Slide 1: ARTIFICIAL INTELLIGENCE CONTENTS :CONTENTS INTRODUCTION TO A.I. EVOLUTION OF A.I. BRANCHES OF A.I. APPLICATIONS OF A.I. CONCLUSIONS ON A.I. INTRODUCTION :INTRODUCTION WHAT IS A.I. ? A.I.

is a branch of computer science that studies the computational requirements for tasks such as perception, reasoning and learning and develop systems to perform those tasks The field of Artificial intelligence strives to understand and build intelligent entities A.I. Strong A.I. M/C can think and act like human Weak A.I. Some thinking like features can be added to M/C Slide 4:INTRODUCTION TURING TEST * Intelligence is defined as the ability to achieve human level performance in all cognitive tests, sufficient to fool a human interrogator. * The test was devised in response to the question,” Can a computer think ?”. * Result was +ve if interrogator can not tell if responses are coming from the M/C or Human. * Proposed by Alan Turing(1950), a British Computer Scientist. Slide 5:INTRODUCTION TURING TEST One person sits at a computer and types the questions. The computer is connected to two other hidden computers At one computer, Human reads and responds to questions. At the other end, computer with no Human aid runs the program to provide responses. Slide 6:INTRODUCTION DEFINITIONS * AI is a branch of computer science dealing with symbolic, nonalgorithmic methods of problem solving * AI is a branch of computer science that deals with ways of knowledge using symbols rather than numbers and with Heuristics, method for processing information. * AI works with pattern matching methods which attempt to describe objects , events or processes in terms of their qualitative features and logical and computational Relationship. Slide 7:INTRODUCTION What is Intelligence ? To respond to situations very flexibly. To make sense out of ambiguous or contradictory messages. To recognize the relative importance of different elements of situations To find similarities between situations despite difference To draw distinctions between situations despite similarities which may link them. Slide 8:HISTORY 1943 – McCulloh and Pitts, Boolean circuit model of brain. 1950 – Turing’s computing machine and intelligence. 1950’s – Early AI programs including Samuel’s checker program, Newell and Simon’s logic theorist, Gelisnters geometry engine 1956 – Dartmouth conference.

Slide 9:HISTORY 1952-69 – “Look, Ma, no hands!” era. 1958 – McCarthy moves to MIT, LISP was born. 1965 – Robinson’s complete algorithm for logical reasoning. 196674 – AI discovers computational complex. Neural network research almost disappears. 1969-79 - Early development in knowledge based systems. Slide 10:HISTORY 1980-88 : Expert system industry booms. 1988-93 : Expert system industry busts. 1985-88 : Neural networks return to popularity. 1995 : Agents… Agents… Agents. (present) BRANCHES :BRANCHES Logical AI What a program knows about the world in general the facts of the specific situation in which it must act and it’s goal are all represented by sentences of some mathematical logical language. Pattern Recognition When a program makes observation of some kind, it is often programmed to compare what it sees with already stored patterns. BRANCHES :BRANCHES Representation Facts about the world have to be represented in some way. Usually languages of mathematical logic are used. Common Sense, Knowledge and Reasoning This is an era in which AI is farthest from human level. While there has been considerable progress, e.g. in development systems of non monotonic reasoning and theories of action BRANCHES :BRANCHES Planning Planning programs start with general facts about the world. They generate a strategy for achieving the goal, the strategy is just a sequence of action. Epistemology This is a study of the kinds of knowledge that are required for solving problems in the world. Ontology It is the study of kinds of things that exist. In AI, things deal with various kinds of object. BRANCHES :BRANCHES Heuristics Heuristics is a way of trying to discover something or an idea embedded in a program. It predicates that compare two nodes in a search tree to see if one is better than other, e.I. constitutes an advance towards the goal, may be more useful. Genetic Engineering It is a technique for getting programs to solve a task by mating random LISP programs and selecting fittest in millions of generations. APPLICATIONS OF A.I. :APPLICATIONS OF A.I. Expert systems. Natural Language Processing (NLP). Speech recognition. Computer vision. Robotics. Automatic Programming.

APPLICATIONS :APPLICATIONS EXPERT SYSTEMS An Expert System is a computer program designed to act as an expert in a particular domain (area of expertise). Expert systems currently are designed to assist experts, not to replace them, They have been used in medical diagnosis, chemical analysis, geological explorations etc. Domain of E.S. Knowledge base Facts Heuristics Phases in Expert System APPLICATIONS :APPLICATIONS Speech Recognition The primary interactive method of communication used by humans is not reading and writing, it is speech. The goal of speech recognition research is to allow computers to understand human speech. So that they can hear our voices and recognize the words we are speaking. It simplifies the process of interactive communication between people and computers, thus it advances the goal of NLP. APPLICATIONS :APPLICATIONS Natural Language Processing The goal of NLP is to enable people and computers to communicate in a natural (humanly) language(such as, English) rather than in a computer language. The field of NLP is divided in 2 categories — Natural Language understanding. Natural Language generation. APPLICATIONS :APPLICATIONS Computer Vision People generally use vision as their primary means of sensing their environment, we generally see more than we hear, feel or smell or taste. The goal of computer vision research is to give computers this same powerful facility for understanding their surrounding. Here AI helps computer to understand what they see through attached cameras. APPLICATIONS :APPLICATIONS Robotics A Robot is a electro-mechanical device that can by programmed to perform manual tasks or a reprogrammable multi functional manipulator designed to move materials, parts, tools, or specialized devices through variable programmed motions for performance of variety of tasks. An ‘intelligent’ robot includes some kind of sensory apparatus that allows it to respond to change in it’s environment. Slide 21:APPLICATIONS Robotics APPLICATIONS :APPLICATIONS Automatic Programming Programming is a process of telling a computer exactly what you want it to do.Writing a program is a tedious job. It must be designed, written, tested, debugged and evaluated. The goal of automatic planning is to create special programs that act intelligent tools to assist programmers and expedite each phase of programming process. Ultimate aim is computer itself should develop a program in accordance with specifications of programmer.

D. don’t be happy. Diamandis. FRCP(C) Dept. tissues) Mass Spectrometry Automated DNA Sequencing /PCR Laser Capture Microdissection SNPs Comparative Genomic Hybridization . Cancer: Does every cancer have a unique fingerprint? (genomic/proteomic?) Changes are Coming: Changes are Coming Changes seen are driven by recent biological / technological advances: Human Genome Project Bioinformatics Array Analysis (DNA. Canada The New Cancer Diagnostics : The New Cancer Diagnostics We Need: We Need better (more objective) and more biologically-relevant tumor classification schemes for prognosis. Tumour Markers: Present and Future: Tumour Markers: Present and Future Eleftherios P. it attracts anti-social elements. New Method: Multiparametric analysis (thousands of molecules at a time). you see a large number of Robots marching into your house destroying everything you own and looting you. CONCLUSION :CONCLUSION In it’s short existence. It has sharpened understanding of human reasoning.FUTURE :FUTURE The day is not far when you will just sit back in your cozy little beds and just command your personal Robot's to entirely do your ruts . Because now they will have full power to think as human. of Laboratory Medicine & Pathobiology. As you open it. So think trice before giving them power of Cognition. selection of therapy better tumor markers for population screening and early diagnosis Paradigm Shift (2000 and Beyond): Paradigm Shift (2000 and Beyond) Traditional Method: Study one molecule at a time.D. FUTURE :FUTURE But wait. Ph. and of the nature of intelligence in general. Some day there will be a knock to your door. This is because ever since there is an advantage in the Technology. proteins.. Just enjoy the Technology. M. At the same time. it has revealed the complexity of modeling human reasoning providing new areas and rich challenges for the future. of Pathology & Laboratory Medicine. It may end in other way too. University of Toronto.. This is true for Robots too. even as of anti-social elements. Toronto. AI has increased understanding of the nature of intelligence and provided an impressive array of application in a wide range of areas. Mount Sinai Hospital Dept. He will be a perfect companion for you.

T7 RNA polymerase Cy5dUTP red fluorescent cRNA cRNA RNA extraction and labeling to determine expression level sample of interest compared to standard reference Microarray Milestone: June 2003 : Microarray Milestone: June 2003 Following their papers in Nature and NEJM Nature 2002. 2003 Comparative Genomic Hybridization: Comparative Genomic Hybridization A method of comparing differences in DNA copy number between tests (e. EORTC. 2005 onwards Applications of Microarrays: Applications of Microarrays Simultaneous study of gene expression patterns of genes Single nucleotide polymorphism (SNP) detection Sequences by hybridization / genotyping / mutation detection Study protein expression (multianalyte assay) Protein-protein interactions Provides: Massive parallel information Slide14: Microarrays. antibodies) assembled in an addressable format. 415: 530-536 NEJM 2002.Technological Advances: Technological Advances Microarrays: Microarrays What is a microarray? A microarray is a compact device that contains a large number of well-defined immobilized capture molecules (e. Science. Slide8: Science 2004. proteins. PCR products. 10 October. prospective trials under way. Comparative Genomic Hybridization: Comparative Genomic Hybridization Label with . 302: 211. tumor) and reference samples Can use paraffin-embedded tissues Good method for identifying gene amplifications or deletions by scanning the whole genome.000 known human genes.g. You can expose an unknown (test) substance on it and then examine where the molecule was captured. You can then derive information on identity and amount of captured molecule. 306: 630-631 Slide9: Microscope slide DNA microarray Slide10: Cy3-dUTP green fluorescent reverse transcriptase. such as Affymetrix’s GeneChip. now include all 50. 347: 1999-2009 Van’t Veer and colleagues (Netherlands Cancer Institute) will use microarray profiling as a routine tool for breast cancer management (administration of adjuvant chemotherapy after surgery).g. synthetic oligos.

000 bases A map of 9 x 106 SNPs have been described in humans by the International SNP map working group (HapMap) 60. J Pathol 2001.195:80-86 Tissue Microarray: Tissue Microarray Printing on a slide tiny amounts of tissue Array many patients in one slide (e. the rest are in introns .195.65:767779 Molecular Profiling of Prostate Cancer: Molecular Profiling of Prostate Cancer Rubin MA.195:80-86 Single Nucleotide Polymorphisms (SNPs): Single Nucleotide Polymorphisms (SNPs) DNA variation at one base pair level. 500) Process all at once (e.The cap is set on the surface of the tissue and a laser pulse is sent through the transparent cap.000 . The selected cells are now adherent to the transfer cap and can be lifted off the tissue and placed directly onto an eppendorf tube for extraction (B). immunohistochemistry) Works with archival tissue (paraffin blocks) Gene Expression Analysis of Tumors: Gene Expression Analysis of Tumors cDNA Microarray Lakhani and Ashworth Nature Reviews Cancer 2001.g.expanding the thermoplastic polymer. Tumor Heterogeneity (Prostate Cancer): Tumor Heterogeneity (Prostate Cancer) Tumor Cells: Red Benign Glands: Blue Rubin MA J Pathol 2001. found at a frequency of 1 SNP per 1. J Pathol 2001. Rubin MA.80-86 Laser Capture Microdissection: Laser Capture Microdissection LCM uses a laser beam and a special thermoplastic polymer transfer cup (A).2.1:151-157 Arrayed CGH: Arrayed CGH Same as previous slide but use arrays of BAC clones instead of chromosomes Laser Capture Microdissection: Laser Capture Microdissection An inverted microscope with a low intensity laser that allows the precise capture of single or defined cell groups from frozen or paraffin-embedded histological sections Allows working with welldefined clinical material.g.Cy-3 Label with Cy-5 Cot1DNA blocks repeats) Nature Reviews Cancer 2001.1:151-157 Tissue Microarray: Tissue Microarray From Jacquemier1 et al Cancer Res 2005.000 SNPs fall within exons.

Why Are SNPs Useful?: Why Are SNPs Useful? Human genetic diversity depends on SNPs between individuals (these are our genetic differences!) Specific combinations of alleles (called “The Haplotype”) seem to play a major role in our genetic diversity How does this genotype affect the phenotype Disease Disposition? Haplotype Patterns: Haplotype Patterns Person A A T T G A T C G G A T. . C T C A Person C A T T G A T C G G A T. . C C A G C G G A . . . C C A T C G G A . C C A T C G G A . .000 single nucleotide polymorphisms (SNPs) covering all 22 autosomes and the X chromosome in a single experiment Coverage: 1 SNP per 20 kb of DNA Needs: 250 ng of genomic DNA-1 PCR reaction Commercial Microarray for Clinical Use (Pharmacogenomics): Commercial Microarray for Clinical Use (Pharmacogenomics) Roche Product CYP 450 Genotyping (drug metabolizing system) First FDA approved microarray-based diagnostic test. C C A G C G G A . . . Why Are SNPs Useful?: Why Are SNPs Useful? Diagnostic Application Determine somebody’s haplotype (sets of SNPs) and assess disease risk. . . 2004 Proteomics & Protein Microarrays: Proteomics & Protein Microarrays Slide32: High-throughput proteomic analysis Haab et al. C T A A Person B A T T G A T A G G A T. C T A A Person E A T T G A T C G G A T. . . . . . C T C A Persons B and D share a haplotype unlike the other three. . Genome Biology 2000. C T A A Person D A T T G A T A G G A T.1:1-22 Protein array now commercially available from BD Biosciences (2002) Applications of Protein Microarrays : Applications of Protein Microarrays Screening for: Small molecule targets Post-translational modifications Protein-protein interactions Protein-DNA interactions Enzyme assays Epitope mapping Cytokine Specific Microarray ELISA: BIOTINYLATED MAB CAPTURE MAB ANTIGEN Detection system Cytokine Specific Microarray ELISA . . . characterized by three different SNPs. . 296: 1391-1393. . Be careful: These diseaserelated haplotypes are not as yet known! SNP Analysis by Microarray: SNP Analysis by Microarray GeneChip® HuSNPTM Mapping Assay (Affymetrix) More than 100. Science. C C A T C G G A . 2002. .

406:747-752 Green: Underexpression Black: Equal expression Red: Overexpression Left Panel: Cell Lines Right Panel: Breast Tumors Figure Represents 1753 Genes Differential Diagnosis of Childhood Malignancies: Differential Diagnosis of Childhood Malignancies Ewing Sarcoma: Yellow Rhabdomyosarcoma: Red Burkitt Lymphoma: Blue Neuroblastoma: Green Khan et al. Validation of prognosis signature: Validation of prognosis signature performance on unselected consecutive series at 10 years (n=295) Lymph node negative patients (n=151) Lymph node positive patients (n=144) <53 yrs. Conclusion This gene expression profile will outperform all currently-used clinical parameters in predicting disease outcome This may be a good strategy to select nodenegative patients who would benefit from adjuvant therapy. Nature 2002:415-586 Examine lymph node negative breast cancer patients and identified specific signatures for: Poor prognosis BRCA carriers The “poor prognosis” signature consisted of genes regulating cell cycle invasion. Nature 2000. Nature 2002:415-586: Applications (continued) Vant’t Veer L.7:673-679 Applications (continued) Vant’t Veer L. no prior malignancy predictive value compared to classical clinical parameters relevance for treatment tailoring Van’t Veer et al New Engl J Med 2002.347:1999-2009 . Nature Medicine 2001. et al.Recently Published Examples: Recently Published Examples Rationale For Improved Subclassification of Cancer by Microarray Analysis: Rationale For Improved Subclassification of Cancer by Microarray Analysis Classically classified tumors are clinically very heterogeneous – some respond very well to chemotherapy. et al. tumor <5cm. some do not. metastasis and angiogenesis. Hypothesis: Hypothesis The phenotypic diversity of cancer might be accompanied by a corresponding diversity in gene expression patterns that can be captured by using cDNA microarray Then Systematic investigation of gene expression patterns in human tumors Molecular⇓might provide the basis of an improved taxonomy of cancer portraits of cancer Molecular signatures Molecular Portraits of Cancer: Molecular Portraits of Cancer Breast Cancer Perou et al.

lymph node negative Treatment tailoring by profiling Therapeutic implications: Therapeutic implications Who to treat: Prognosis profile as diagnostic tool improvement of accurate selection for adjuvant therapy (less under.Slide42: Cohort of 295 tumors patients < 53 yrs. lymph node negative or positive Unselected consecutive patient series.303:1754-5 Mass Spectrometry for Proteomic Pattern Generation: Mass Spectrometry for Proteomic Pattern Generation Serum analysis by SELDI-TOF mass spectrometry after extraction of lower molecular weight proteins Data analyzed by a “pattern recognition” algorithm ProteinChip® Arrays: SELDI affinity chip surfaces (Ciphergen): ProteinChip® Arrays: SELDI affinity chip surfaces (Ciphergen) Reverse Phase Anionic Cationic IMAC Normal Phase Slide50: Proteins are captured.400 per test 215.164:35-42 Commercial Products: Commercial Products Mammaprint marketed by Agendia. Amsterdam.and overtreatment) Prognosis profile implemented in clinical trials reduction in number of patients & costs (select only patients that are at metastases risk) How to treat: Predictive profile for drug response selection of patients who benefit Commercial Products: Commercial Products Oncotype DX by “Genomic Health Inc”.Van’t Veer publications Test costs Euro 1650. based on 70 gene signature Prospective trials underway Celera and Arcturus developing similar tests (prognosis/prediction of therapy) Science 2004. Redwood City. retained and purified directly on the chip (affinity capture ) Laser The SELDI Process and ProteinChip® Arrays Sample goes directly onto . $3. CA A prognostic test for breast cancer metastasis based on profiling 250 genes. 16 genes as a group have predictive value.000 breast cancer cases per year (potential market value > $500 million!) Test has no value for predicting response to treatment Am J Pathol 2004. mean follow-up ~ 7 yrs 295 tumors 70 prognosis genes Kaplan-Meier survival curves for all 295 patients: Kaplan-Meier survival curves for all 295 patients Slide44: premenopausal. The Netherlands Based on L.

Prediction of cancer outcome with microarrays: a multiple random validation strategy: Findings: Because of inadequate validation.359:572-577 Slide53: Diamandis. . EP J Natl Cancer Inst 2004. Lancet. 365: 454-455 Prediction of cancer outcome with microarrays: a multiple random validation strategy: Prediction of cancer outcome with microarrays: a multiple random validation strategy Findings: The list of genes identified as predictors of prognosis was highly unstable. Michiels et al. Lancet.the ProteinChip® Array Surface is “read” by Surface-Enhanced Laser Desorption/Ionization (SELDI) ProteinChip® Array Slide51: Detector Laser Flight Tube Mass Spectrometry-Based Proteomics and Bioinformatics The Future of Biomarkers m/z Relative Intensity Target Results: Ovarian Cancer: Results: Ovarian Cancer Petricoin III EF. Ioannides Lancet 2005. EP Mol Cell Proteomics 2004. 2005. et al. molecular signatures strongly depended on the selection of patients in the training sets Michiels et al. this technology performs no better than flipping a coin. 96: 353-356 Reviews / Opinions / Commentaries Diamandis. The other two studies barely beat horoscopes… J. 2005. 306: 630-631 Prediction of cancer outcome with microarrays: a multiple random validation strategy: Michiels et al. EP Clin Chem 2003. our chosen studies published overoptimistic results compared with those from our own analyses. 3:367-78 Microarray discrepancies (185 genes): Microarray discrepancies (185 genes) Science 2004.P. Prediction of cancer outcome with microarrays: a multiple random validation strategy Description of eligible studies : Description of eligible studies Microarrays & molecular research: noise discovery?: Microarrays & molecular research: noise discovery? In 5 of the 7 largest studies on cancer prognosis. 49: 1272-1275 Diamandis. Lancet 2002. 365: 488-492. 365: 488-492.

You can use gears to: Speed up or slow down your robot. There are many different types of gears Spur Gear Bevel Gear Worm Gear Rack & Pinion . 365: 488-492. Prediction of cancer outcome with microarrays: a multiple random validation strategy The Future??: Imaging Multiparametric/miniature testing of serum on a protein array Mass spectrometric serum/urine proteomic pattern generation The Future?? The Future??: Asymptomatic individuals Predisposition to certain disease Prevention (drugs. lifestyle) Surveillance Whole genome SNP analysis The Future?? The Future??: The Future?? Cancer patient Cancerous tissue Tumour fingerprint Individualized treatment Surgery / Biopsy Array analysis Different Types of Robots: Different Types of Robots Robot Arms (Fixed Robots) Mobile Robots Humanoid Robots Legged Robots Wheel Robots 3 wheels 2 Driver wheels. 2005. w) = cte. Make your robot stronger or weaker. 1 Caster 1 Driver wheel. 2 Casters 4 wheels Casters make diverse problems in the control of the robot Wheel Robot Main Components: Wheel Robot Main Components Main Components Mechanics Wheels Driver Motor (s) Power Transmission System Electronics Controller Board Needing feedback from environment Sensors We are now discussing some of the above topics Different Types of Motors: Different Types of Motors DC Motors You can simply control it AC Motors It’s difficult to be controlled but it can be used in high power applications Servo Motors You have complete control on the shaft angle Different Types of Feed Back: Different Types of Feed Back Sensors IR Sensors Pressure Sensors Light Sensors Temperature Sensors Encoder What is Encoder: What is Encoder Why do we use Power Transmission Systems?: Why do we use Power Transmission Systems? To reduce Angular Velocity To increase Torque P = (T .Lancet. Different Transmission Systems Gear Hard manufacturing and adjustment Pulley So w => T Gear: Gear Gears are used to change the speed and force of the motor.

And have another person . They have many special properties.Gear: Gear Spur gears are wheels with teeth Gear: Gear Bevel gears mesh at right angles. It also means the last axle has 75 times the torque as the first axle. This creates an equal (and opposite) force in the large gear. idler gears do not change the gear ratio Gear: Gear The gear ratio of this gear box is 75 to 1 That means the last axle rotates 75 times slower than the first axle. Have one person turn this wheel. the output axle rotates in the opposite direction as the input axle. …produces a force at the tooth. This is the gear ratio! Idler Gear: Idler Gear An idler gear is a gear that is inserted between two other gears. so they change the direction of rotation.. Idler Gear: Idler Gear Recall that when using spur gears. F t The moment arm is the radius of the gear. Slide18: Try this experiment. The force acts through this larger moment arm... Gear: Gear Worm gears look like screws. Slide13: F t r The force from the small gear’s tooth pushes against the large gear’s tooth.. Slide12: Where does all this “torque” come from? Consider a pair of gears that are meshed together. This is Newton’s 3rd Law... You can also use idler gears to change the spacing between the input and output axles Remember. … and produces a larger torque on this axle. Remember: t = F x r r A torque on this axle. Gear: Gear Rack & pinion gears turn rotational motion into straight-line motion. Slide14: Analyzing the forces. The gear ratio would be computed just the same if there were no idler gear. t1 = F1 x r1 t2 = F2 x r2 F1 = t1 / r1 F2 = t2 / r2 F1 = F2 t1 / r1 = -t2 / r2 -t2 / t1 = r2 / r1 The ratio of torques is the ratio of the gear radii. Idler gears do not affect the gear ratio between the input and output gears.

ir Please take a look at our website at: Robot. 7: Assessment of Intelligence Slide 2:Brief. Slide19: Gears can increase the torque (and force) that they exert on something.schoolnet. it comes at a price.w1=D2. This is known as mechanical advantage.try to hold on to this wheel.ir Slide 1:Ch.w2 Belt Drive Basics: Belt Drive Basics Motor Nameplate Size DR DN Belt Drive Basics: Belt Drive Basics 700 rpm 4375 rpm Ratio always greater than 1 Speed Ratio = 2.5 How to assemble our Robot: How to assemble our Robot Here is our package How to assemble our Robot: How to assemble our Robot 1 2 3 How to assemble our Robot: How to assemble our Robot Bottom view of the robot How to assemble our Robot: How to assemble our Robot Sensor board assembly If you have any further help please contact us at:: If you have any further help please contact us at: robot@schoolnet. Do you know what it is? torque increases Slide20: Belt Drives Uses friction to transmit power Velocity Ratio: D1. Brief History of Intelligence Testing Concept of Intelligence The IQ – meaning and correlates Clinical Assessment of Intelligence – major instruments and issues Ch. 7 Overview: Assessment of Intelligence . BUT.

com/watch?v=pRBcosUeE_0 Slide 7:David Wechsler’s Definition of Intelligence “Intelligence is the aggregate or global capacity of the individual to act purposefully.youtube.adjustment/adaptation to new environments .ability to learn/educability . No universally accepted definition of intelligence Common references for defining intelligence . Legal/Civil Rights Arena – Fairness of IQ testing for diverse populations Brief.Slide 3:Historical Developments Leading to IQ Testing Alfred Binet/Theodore Simon and the Educational need for IQ testing Psychological science increasingly demonstrates mental abilities can be measured with IQ tests.com/watch?v=gYZtcTxWf4U Slide 5:Differences – ability.abstract thinking Definitions of Intelligence Slide 6:Interactive Intelligence Test http://www. to think rationally and to deal effectively with his . aptitude. & achievement.youtube. Brief History of Intelligence Testing Slide 4:When Intelligence Testing Goes Wrong http://www.

Sternberg – Triarchic Theory (3: componential [analytical]. Gardner: Theory of Multiple Intelligences (families of 6 intelligences) Slide 12:.L.Global because it characterizes individual’s behavior as a whole . 2 2nd factors “fluid” and “crystallized” abilities .B. Guilford – 3 intelligence components operations. experiential [creative .R.Aggregate because it is composed of elements or abilities that are qualitatively differentiable Slide 8:David Wechsler’s Definition of Intelligence http://www.youtube.com/watch? v=KEFpaY3GI-I&feature=related Slide 11:Theoretical Approaches – H. Thurstone – 7 group factors R. 17-primary factors.youtube. Cattell – g. Gardner: Theory of Multiple Intelligences (families of 6 intelligences) http://www.J.environment. contents.” .com/watch?v=ONwiuiZ6mJ0 Slide 9:Factor Analytic Approaches – Spearman “g” and “s” factors .J.L. and products Approaches/Theories of Intelligence Slide 10:Theoretical Approaches – H.

youtube. contextual [practical – street smarts]) Approaches/Theories of Intelligence Slide 13:Time to Assess Your IQ – whatever that means http://www.com/watch? v=ZgZkNwfjPvw Slide 14:Cracker Barrel IQ Test-III-R Slide 15:Binet (MA: Mental Age) Stern (IQ: Mental Age/Chronological Age x 100) The Intelligent Quotient (IQ): Its Meaning and Development Slide 16:Weshsler (Deviation IQ) The Intelligent Quotient (IQ): Its Meaning and Development Slide 17:The Intelligent Quotient (IQ): Empirical Correlates Slide 18:School Success (IQ & grades r = .50) Occupational Success (best – for job entry) Group Differences? Influence of Heredity on IQ scores (5181%) Stability of IQ scores The Intelligent Quotient (IQ): Empirical Correlates .thinking].

Slide 19:Standford-Binet Scales . Specificity of Measurement Issues in Clinical Use of Intelligence Tests Artificial Intelligence :1 Artificial Intelligence CSC 4601 List of Books :2 List of Books Artificial Intelligence (A modern Approach). 2nd Edition. 3rd . reliability/validity Types of Modern IQ Tests Slide 21:Wechsler Scales . by Stuart Russell and Peter Norvig.descriptions.Adults (WAIS-III/IV) Children (WISC-IV) Types of Modern IQ Tests Slide 22:Structure of the Scale WAIS–III Levels of Performance FSIQ Digit Span Arithmetic Letter– Number Sequencing Vocabulary Similarities Information Comprehension Digit Symbol—Coding Symbol Search Block Design Matrix Reasoning Picture Completion Picture Arrangement VIQ PIQ VCI WMI POI PSI 8 Slide 25:Estimation of General Intelligence Level Prediction of Academic Success Appraisal of Style and Abstraction Role of the Situation Generality vs. standardization. Artificial Intelligence.

The mouse tries various paths as shown by arrows and can reach the cheese by more than one path. In other words the mouse can find more than one solutions to this problem. Winston. This problem can be considered as a common real life problem which we deal with many times in our life. or in this case to the piece of cheese. Artificial Intelligence : Structures and Strategies for Complex Problem Solving. Hence the ability of problem solving demonstrates intelligence. . Chapters (List of Contents) :3 Chapters (List of Contents) 1 Introduction 2 Problem Solving 3 Genetic Algorithms 4 Knowledge Representation and Reasoning 5 Expert Systems 6 Handling uncertainty with fuzzy systems 7 Introduction to learning 8 Planning 9 Advanced Topics 10 Conclusion 1.Edition. to a friends house.1 What is intelligence? :4 1. 5th Edition. i.e. We can say that the mouse is intelligent enough to find a solution to the problem. to a market. may be to a university. finding a path. George Luger. Artificial Intelligence.1 What is intelligence? The ability of problem solving demonstrates intelligence Example-1 Consider a mouse trying to search/reach the piece of cheese placed at right top corner of the image. Elaine Rich and Kevin Knight.

recalling).1 What is intelligence?.1 What is intelligence?. Example-3: Find the next number in the sequence given below: 1. When we try to solve something.1 What is intelligence?.. Blood Pressure (BP).… The next number is obviously 25 but is achieved through thinking. 9. and many other things to solve different problems. The Capabilities like thinking....1 What is intelligence… :8 1. we check various ways to solve it.. and decision making. 1. 4. and decision making come in intelligence. Biological example of Intelligence and AI… How insects apply Rosenblatt’s/Hebbian Learning ? 1. numerical processing. :7 1. numerical processing. memory recalling. 16..Slide 5:5 1.. Example-2 Biological example of Intelligence and AI… How insects apply Rosenblatt’s/Hebbian Learning ? Slide 6:6 1.1 What is intelligence?. Pulse Rate .1 What is intelligence… Example-4 A doctor checks a patient The doctor collects some knowledge about the patient by asking some questions and measuring temperature (T). we check different combinations. memory manipulation (storing..

Some people might think that the people around 4ft are short. 1.1 What is intelligence… :9 Example-5: Ambiguous and fuzzy problems demonstrates intelligence Things are not so simple. medium or tall? You might think that you are tall but your friend who is taller than you might say that NO! You are not. telling us that good memory.5ft are short. Are you short. we have just mentioned a very simple case here. people don’t think in the same manner. Diagnosing a disease has many other complex information and observations involved. will be better able to classify a patient. Even having the same measurements. His previous knowledge is based on rules like: “If the patient has a high BP and normal T and normal PR then he is not well”.(PR) etc. different people can get completely different results because they approach the problem in different fashions.5ft are medium and around 6. Hence. Things can be . It is important to consider here that a doctor who would have a better memory to store all this precious knowledge. Others might say that the people around 4. and efficient memory and information manipulation also comes in intelligence. better ability of retrieving the correct portion of the knowledge for the correct patient. Then based on his previous knowledge he tries to diagnose the disease. and around 6ft are tall. Moreover.5ft are tall. around 5. good recall. around 5ft are medium.

Answer is No. It should have distributed and parallel architecture. Not at all. It can recognizes fingerprints. It can get trained. 1. 1.2 Intelligent Machines A machine is intelligent if It can find a path by searching through a mesh. Hence the ability to tackle ambiguous and fuzzy problems demonstrates intelligence. It should be general purpose and multitasking having. Preferably. like a doctor. It can upgrade its previous learning.3 Formal Definitions of AI :11 1. faces. we wish it to behave like human! A machine having such properties is called an intelligent machine. It can develop plans/schedule like a time-table. But do you think this is the real natural intelligence?. having observed same measurements and solves the same problem in two different ways and reaches different solutions. Instead this is Artificial intelligence.even more complex when the same person. It can answers ambiguous questions. It can diagnose and prescribe.3 Formal . Our intelligence actually helps us to do this.1 What is intelligence… 1. and optical character. It can solve problems like the next number in the sequence. It can perceives knowledge.2 Intelligent Machines :10 1. In short. It can understands. We all know that we answer such fuzzy questions very efficiently in our daily lives.

“The branch of computer science that is concerned with the automation of intelligent behavior” (Luger and Stubblefield. 1985).trying to catch out our own thoughts as they go by.Definitions of AI The exciting new effort to make computers think… machines with minds. There are two ways to do this: (i) through introspection . 1993). For this we need to get inside the actual functioning of the human mind. 1991). “The art of creating machines that perform functions that require intelligence when performed by people” (Kurzweil 1990). The study of computation that make it possible to perceive reason and act” (Winston 1992). And (ii) through psychological experiments: that concern with the activities of . “The study of mental faculties through the use of computational models” (Charniak and McDermott). 1990). learning …” (Bellman. people are better” (Rich and Knight.3 Formal Definitions of AI … Thinking Humanly To make computers think like human we need a way of determining how human think. in the full and literal sense” (Haugeland. “A field of study that seeks to explain and emulate intelligent behavior in terms of computational processes” (Schalkoff. 1. The study of how to make computers do things at which. at the moment. activities such as decision making. problem solving. [The automation of] activities that we associate with human thinking. 1978).3 Formal Definitions of AI … :12 1.

when a natural language processing system makes a dialog with a person. It has inherited its ideas. For instance. etc. or when a robotic arm sorts out manufactured goods coming over a conveyer belt. 1.brain. learn. it becomes possible to express the theory as a computer program that follows the same rules. let us give a fairly comprehensive comment that Artificial Intelligence is a field which deals with the study and development of systems that can perceive. philosophy.3 Formal Definitions of AI … Acting Humanly The issue of acting like human comes up when AI programs have to do something physically which human usually do in real life. think. 1. linguistics. mathematics. analyze and act like a real human. Keeping in view all the above motivations. From philosophy.4 History and Evolution of AI AI is a young field. we . or when some intelligent software gives out a medical diagnosis. Once we have a precise theory of mind. psychology. concepts and techniques from many disciplines like biology.3 Formal Definitions of AI … :13 1.4 History and Evolution of AI :14 1. The interdisciplinary field of cognitive science brings together computer models from AI and experimental techniques from psychology to try to construct precise and testable theories of the working of human mind.

but they didn’t pursued this idea much at that time.4. 1.have theories of reasoning and learning . we have formal theories of logic. probability. . From psychology. They claimed (without providing an evidence) that any logical task can be performed by suitably connecting a sufficient number of neurons. Linguistics provides us with the theories of structure and meaning of language.1 First recognized work on AI The first work that is now generally recognized as AI was done by Warren McCulloch and Walter Pitts (1943). Donald Hebb (1949) demonstrated a simple updating rule (training method) for modifying the connection strengths (weights) between neurons such that learning could take place. From mathematics. They proposed a neuron model. and computation. on or off and that the state of the neuron is the response of sufficient stimulation by a number of neighboring neurons.1 First recognized work on AI :15 1.4. From biology we have information about the network structure of human brain and all the theories on functionalities of different human organs.e. They showed that the neuron is a bi-state element i. we have the tools and techniques to investigate the human mind and ways to represent the resulting theories. decision-making. Finally from computer science we have tools and concepts to make AI a reality.

3 First program that thought humanly :17 1. Newell and Simon’s early success was followed up with the General Problem Solver. Over the next twenty years these people.S researchers got together and organized a two-month workshop at Dartmouth. CMU. Many of them met great successes.4. There were altogether only 10 attendees. this program was developed in the manner that it attacked a problem imitating the steps that human take when solving a . 1.1. The program came up with proofs for logic theorems. Although all the researchers had some excellent ideas and a few even had some demo programs like checkers. Allen Newell and Herbert Simon actually dominated the workshop. The researchers were highly motivated to try out AI techniques to solve problems that were not yet been solved. but Newell and Herbert already had a reasoning program. their students and colleagues at MIT.2 The name of the field as Artificial Intelligence : 16 1.3 First program that thought humanly In the early years AI met drastic success.4.2 The name of the field as Artificial Intelligence In 1956 some of the U. The most lasting and memorable thing that came out of that workshop was an agreement to adopt the new name for the field: Artificial Intelligence. Unlike Logic Theorist. the Logic Theorist. Stanford and IBM.4.4. dominated the field of artificial intelligence.

problem. Though it was catered for a limited class of problems but it was found out that it addressed those problems in a way very similar to that as human. It was probably the first program that imitated human thinking approach. 1.4.4 Development of Lisp :18 1.4.4 Development of Lisp In 1958 In MIT AI Lab, McCarthy defined the high-level language Lisp that became the dominant AI programming language in the proceeding years. Though McCarthy had the required tools with him to implement programs in this language but access to scarce and expensive computing resources were also a serious problem. Thus he and other researchers at MIT invented time sharing. Also in 1958 he published a paper titled Programs with Common Sense. This Program can be seen as the first complete AI system. Unlike the other systems at that time, it was to cater general knowledge of the world. For example, he showed that how some simple rules could help a program generate a plan to drive to an airport and catch the plane. 1.5 Applications :19 1.5 Applications Artificial finds its application in a lot of areas. A few of the applications will be mentioned here. Many information retrieval systems like Google search engine uses artificially intelligent crawlers and content based searching techniques to efficiency and

accuracy of the information retrieval. A lot of computer based games like chess, 3D combat games use intelligent software to make the user feel as if the machine on which that game is running were intelligent. Computer Vision is a new area where people are trying to develop the sense of visionary perception into a machine. Natural language processing is another area which tries to make machines speak and interact with humans just like humans themselves. This requires a lot from the field of Artificial Intelligence. 1.5 Applications :20 1.5 Applications Computer vision applications help to establish tasks which previously required human vision capabilities e.g. recognizing human faces, understanding images and to interpret them, analyzing medical scan and many tasks. Expert systems form probably the largest industrial applications of AI. Software like MYCIN and XCON/R1 has been successfully employed in medical and manufacturing industries respectively. Robotics again forms a branch linked with the applications of AI where people are trying to develop robots which can be rather called as humanoids. Organizations have developed robots that act as pets, visitor guides etc. 1.6 Summary :21 1.6 Summary Intelligence can be understood as a trait of some living species Many

factors and behaviors contribute to intelligence Intelligent machines can be created To create intelligent machines we first need to understand how the real brain functions Artificial intelligence deals with making machines think and act like humans It is difficult to give one precise definition of AI History of AI is marked by many interesting happenings through which the field gradually evolved In the early years people made optimistic claims about AI but soon they realized that it’s not all that smooth AI is employed in various different fields like gamming, business, law, medicine, engineering, robotics, computer vision and many other fields AI has enormous room for research and posses a diverse future Slide 1: ARTIFICIAL INTELLIGENCE CONTENTS :CONTENTS INTRODUCTION TO A.I. EVOLUTION OF A.I. BRANCHES OF A.I. APPLICATIONS OF A.I. CONCLUSIONS ON A.I.

INTRODUCTION :INTRODUCTION WHAT IS A.I. ? A.I. is a branch of computer science that studies the computational requirements for tasks such as perception, reasoning and learning and develop systems to perform those tasks The field of Artificial intelligence strives to understand and build intelligent entities A.I. Strong A.I. M/C can

The computer is connected to two other hidden computers At one computer. method for processing information. nonalgorithmic methods of problem solving * AI is a branch of computer science that deals with ways of knowledge using symbols rather than numbers and with Heuristics. * Result was +ve if interrogator can not tell if responses are coming from the M/C or Human. a British Computer Scientist. * AI works with pattern matching methods which . computer with no Human aid runs the program to provide responses.” Can a computer think ?”. sufficient to fool a human interrogator. * Proposed by Alan Turing(1950).I. Some thinking like features can be added to M/C Slide 4:INTRODUCTION TURING TEST * Intelligence is defined as the ability to achieve human level performance in all cognitive tests. At the other end. * The test was devised in response to the question. Human reads and responds to questions. Slide 5:INTRODUCTION TURING TEST One person sits at a computer and types the questions.think and act like human Weak A. Slide 6:INTRODUCTION DEFINITIONS * AI is a branch of computer science dealing with symbolic.

1950’s – Early AI programs including Samuel’s checker program. Neural network research almost disappears. Newell and Simon’s logic theorist. Ma. LISP was born.Early development in knowledge based systems. Slide 7:INTRODUCTION What is Intelligence ? To respond to situations very flexibly. Gelisnters geometry engine 1956 – Dartmouth conference. . 1950 – Turing’s computing machine and intelligence. 1966-74 – AI discovers computational complex. 1958 – McCarthy moves to MIT.attempt to describe objects . To make sense out of ambiguous or contradictory messages. Slide 8:HISTORY 1943 – McCulloh and Pitts. 1965 – Robinson’s complete algorithm for logical reasoning. 1969-79 . events or processes in terms of their qualitative features and logical and computational Relationship. To recognize the relative importance of different elements of situations To find similarities between situations despite difference To draw distinctions between situations despite similarities which may link them. no hands!” era. Slide 9:HISTORY 1952-69 – “Look. Boolean circuit model of brain.

1988-93 : Expert system industry busts. it is often programmed to compare what it sees with already stored patterns. 1985-88 : Neural networks return to popularity.Slide 10:HISTORY 1980-88 : Expert system industry booms. Knowledge and Reasoning This is an era in which AI is farthest from human level. (present) BRANCHES :BRANCHES Logical AI What a program knows about the world in general the facts of the specific situation in which it must act and it’s goal are all represented by sentences of some mathematical logical language. Common Sense. in development systems of non monotonic reasoning and theories of action BRANCHES :BRANCHES Planning Planning programs start with general facts about the world. 1995 : Agents… Agents… Agents. the .g. Usually languages of mathematical logic are used. While there has been considerable progress. BRANCHES :BRANCHES Representation Facts about the world have to be represented in some way. They generate a strategy for achieving the goal. Pattern Recognition When a program makes observation of some kind. e.

Expert systems. BRANCHES :BRANCHES Heuristics Heuristics is a way of trying to discover something or an idea embedded in a program. may be more useful. geological explorations . Ontology It is the study of kinds of things that exist. Epistemology This is a study of the kinds of knowledge that are required for solving problems in the world. Computer vision. chemical analysis.I. It predicates that compare two nodes in a search tree to see if one is better than other. Robotics. In AI. constitutes an advance towards the goal.strategy is just a sequence of action.I. Genetic Engineering It is a technique for getting programs to solve a task by mating random LISP programs and selecting fittest in millions of generations. Natural Language Processing (NLP). e. APPLICATIONS :APPLICATIONS EXPERT SYSTEMS An Expert System is a computer program designed to act as an expert in a particular domain (area of expertise). Expert systems currently are designed to assist experts. :APPLICATIONS OF A. Automatic Programming. Speech recognition. They have been used in medical diagnosis. not to replace them. things deal with various kinds of object. APPLICATIONS OF A.I.

English) rather than in a computer language. feel or smell or taste. we generally see more than we hear. The goal of speech recognition research is to allow computers to understand human speech. The field of NLP is divided in 2 categories— Natural Language understanding. it is speech.S. The goal of computer vision research is to give computers this same powerful facility for .etc. APPLICATIONS :APPLICATIONS Computer Vision People generally use vision as their primary means of sensing their environment. So that they can hear our voices and recognize the words we are speaking. It simplifies the process of interactive communication between people and computers. thus it advances the goal of NLP. Domain of E. Knowledge base Facts Heuristics Phases in Expert System APPLICATIONS :APPLICATIONS Speech Recognition The primary interactive method of communication used by humans is not reading and writing. APPLICATIONS :APPLICATIONS Natural Language Processing The goal of NLP is to enable people and computers to communicate in a natural (humanly) language(such as. Natural Language generation.

APPLICATIONS :APPLICATIONS Robotics A Robot is a electro-mechanical device that can by programmed to perform manual tasks or a reprogrammable multi functional manipulator designed to move materials. parts. tools. The goal of automatic planning is to create special programs that act intelligent tools to assist programmers and expedite each phase of programming process.understanding their surrounding. An ‘intelligent’ robot includes some kind of sensory apparatus that allows it to respond to change in it’s environment. Ultimate aim is computer itself should develop a program in accordance with specifications of programmer. tested.Writing a program is a tedious job. Here AI helps computer to understand what they see through attached cameras. written. or specialized devices through variable programmed motions for performance of variety of tasks. debugged and evaluated. It must be designed. Slide 21:APPLICATIONS Robotics APPLICATIONS :APPLICATIONS Automatic Programming Programming is a process of telling a computer exactly what you want it to do. .

it attracts anti-social elements. FUTURE :FUTURE But wait. and of the nature of intelligence in general. It may end in other way too. He will be a perfect companion for you. It has sharpened understanding of human reasoning.FUTURE :FUTURE The day is not far when you will just sit back in your cozy little beds and just command your personal Robot's to entirely do your ruts . This is because ever since there is an advantage in the Technology. As you open it. This is true for Robots too. At the same time. So think trice before giving them power of Cognition. it has revealed the complexity of modeling human reasoning providing new areas and rich . AI has increased understanding of the nature of intelligence and provided an impressive array of application in a wide range of areas. don’t be happy. Because now they will have full power to think as human. Some day there will be a knock to your door. even as of anti-social elements. you see a large number of Robots marching into your house destroying everything you own and looting you. Just enjoy the Technology. CONCLUSION :CONCLUSION In it’s short existence.

waiting for it to decode a message from the perpetrators of a grisly terrorist attack. It's simply written in Spanish:. One of the very earliest pursuits in computer science.or rather. Carbonell's machine -. chief science officer of Meaningful Machines." Me Translate Pretty One Day . if not perfect. "Jaime Carbonell. But a New York firm with an ingenious algorithm and a really big dictionary is finally cracking the code.12).. The Language Technologies Institute (LTI) at Carnegie Mellon University. Language translation is a tricky problem. including users. developers." • After you read the article." A definition from the European Association for Machine Translation (EAMT). By Evan Ratliff. Wired (December 2006.. .Steve Silberman "What is Machine Translation? Machine translation (MT) is the application of computers to the task of translating texts from one natural language to another. Issue 14. "an organization that serves the growing community of people interested in MT and translation tools. MT has proved to be an elusive goal. The message isn't encrypted or scrambled or hidden among thousands of documents. not only for a piece of software but also for the human mind.is attempting a task that has bedeviled computer scientists for half a century. Machine Translation (a subtopic of Natural Language) "A renewed international effort is gearing up to design computers and software that smash language barriers and create a borderless global marketplace. and The Center for Computational Learning Systems (CCLS) at Columbia University. be sure to visit Meaningful Machines. Running software that took four years and millions of dollars to develop. hunches over his laptop in the company's midtown Manhattan offices." . but today a number of systems are available which produce output which. the server farm it's connected to a few miles away -. and researchers of this increasingly viable technology.. is of sufficient quality to be useful in a number of specific domains.Spanish to English? French to Russian? Computers haven't been up to the task.challenges for the future.

. The main drivers for this more pragmatic approach to machine translation have been the enlargement of the European Union and the spread of the internet. he says. developed by the Advanced Telecommunications Research Institute International near Kyoto. began using 'machine translation' software in 1998 and has so far translated 5 million automobile assembly instructions into Spanish. [T]he fact that a pocket-sized device could interpret tourist-type phrases accurately and on the fly. Computerworld (August 13. Over time. 'It’s not perfect.' Richardson says. and then have another system that 'adjudicates' among them in real time to find the best translation. but it’s good enough.' says Steve Richardson. 'We have serviced thousands and thousands of customers with articles we have machine-translated.. Ford Motor Co. it was encouraging to hear Shinzo Abe..' . They get an answer without calling in. Statistical machine translation is a newer technique that’s not yet in widespread use. "For those who put their faith in technology." Translation Tools . Portuguese and Mexican Spanish. And the technology is most appropriate when translations don’t have to be perfect. In turn.. demonstrate his linguistic skills a few weeks ago with a palm-sized gizmo that provided instantaneous translations of spoken Japanese into near-flawless English and Chinese.are beamed overnight to plants around the world. . a senior researcher at Microsoft. are the wave of the future. translation tools can be fantastic productivity aids. Systran’s tool uses a tried-and-true translation technique called rules-based translation. says much about the improvements that have been made lately in machine translation. 'The new direction in the research community is to see how you can combine these purely statistical techniques with some linguistic knowledge. This device.. But use them with caution.Mark my words.. 'It’s modeling the rules with the statistical methods.. And researchers say new approaches to this old discipline are greatly improving the performance of the tools.. therefore. 2007). In essence.. Automated translation tools have been around for a long time... . a technical specialist in artificial intelligence (AI) at Ford.. By Gary Anthes. and their translations -some 5... It uses collections of documents and their translations to 'train' software. . [H]ybrid systems.at least not right away. from one language to several others.' says Nestor Rychtyckyj. researchers say.New Approaches to an Old Discipline. Machine translation has been an elusive goal since the earliest days of computer science.. . and new techniques are boosting their performance.. The Economist (February 16.. this has spawned a wealth of new translation approaches. 'It wouldn’t be feasible to do this all manually.. "Language translation software isn’t likely to allow you to lay off your bilingual staffers -. What’s that worth to the company' . Automated translation in the corporate world succeeds to the extent that users are willing to carefully customize systems to their unique needs and vocabularies. which combine translation memories and machine translation based on rules or statistics or both. . these data-driven systems 'learn' what makes a good translation and what doesn’t and then use probability and statistics to decide which of several possible translations of a given word or phrase is most likely correct based on context. SRI’s approach is to do machine translations with the best available rules-based and statistical-based systems. Japan’s prime minister." . But applied with discrimination and lots of preparation.. 2007). Both have generated a pressing need for cheap and cheerful translations between numerous languages.000 pages a day -. German. Assembly manuals are updated in English every day. . and they are becoming more sophisticated and complex.

• Also see: Machine Translation for Manufacturing . . Xeni Jardin's Xeni Tech report for NPR's Day to Day (November 13. The use of machine translation was made necessary by the vast amount of dynamic information that needed to be translated in a timely fashion. "The past few years have shown that U. In the late 1990s.." Tech Solutions to Iraqi-U.com (November 5.A Case Study at Ford Motor Company. Defense Advanced Research Project Agency. That's why the military would love software that can listen to TV broadcasts or phone conversations and read Web sites in Arabic and Chinese. and President. Last year DARPA launched a project that aims to create that real-time translation software. By Brian Bergstein. AI Magazine 28(3): Fall 2007. Top minds taxed by translation challenge . 2006). Information Processing Technology Office. Few military personnel have enough fluency with Iraqi Arabic to be easily understood. One of the biggest challenges is recognizing vital information in foreign languages -. Spanish. researchers have been building and utilizing computer systems that can translate from one language to another without requiring extensive human intervention. with Rodney Brooks (Director. MIT Artificial Intelligence Laboratory & Fujitsu Professor of Computer Science & Engineering. we focus on how AI techniques. for Global Autonomous Language Exploitation. 2004).S.and acting quickly on it.S.. The segment begins at 20:34.Abstract: "Machine translation (MT) was one of the first applications of artificial intelligence technology that was deployed to solve real-world problems.Creating a real-time translating machine is harder than it seems. A hand-held voice translator device developed by Integrated Wave Technologies. Language Barrier. "Part of the daily struggle for soldiers and Marines in Iraq is communicating with civilians and suspected insurgents. It’s called GALE. 31. MIT). such as knowledge representation and natural language processing can improve the accuracy of machine translation in a dynamic environment such as auto manufacturing. 2006: audio available). Dutch. and field translators are in short supply. Microsoft Research). government intelligence goes only so far. The MT system has already translated more than 7 million instructions into these languages and is an integral part of the overall manufacturing process-planning system used to support Ford’s assembly plants in Europe. The assembly build instructions at Ford contain text written in a controlled language as well as unstructured remarks and comments. Since the early 1960s. and Ron Brachman (Director. American Association for Artificial Intelligence). . Adaptive Systems & Interaction Group. and Portuguese. to adapt and customize its machine-translation technology in order to translate Ford’s vehicle assembly build instructions from English to German. Eric Horvitz (Senior Researcher and Group Manager. Ford Vehicle Operations began working with Systran Software Inc." Watch Ron Brachman demonstrate the Phraselator® on The Charlie Rose Show episode: A panel discussion about Artificial Intelligence (December 21. The Associated Press /available from MSNBC. But technology may help close that communications gap. translate them into English and summarize the key elements for humans. Mexico and South America. By Nestor Rychtyckyj. In this paper.

. The software. written to recognize specific rules of grammar and usage. translating them. IraqComm can be deployed anywhere and everywhere. there simply aren't enough who are willing to assist in every important conversation.Laptop software that can translate English-Arabic conversations on the fly is being tested in Iraq.com (May 29.. By Tom Abate. . After DynaSpeak converts the spoken words into text. In this talk. The first module uses rule-based algorithms. The goal of IraqComm is not to put human translators out of business. "During a recent product demonstration at SRI headquarters in Menlo Park. and playing the translation in a matter of seconds. it can give the military more translation options and help to mitigate the wartime hazard for Iraqi translators. software written by SRI International scientists piped the question through the computer's speaker -. Palo Alto-based SRI International announced that it had deployed 32 Windows XP laptops loaded with advanced translation software for military evaluation in Iraq.. 2006: How to Talk Like an Iraqi . developed with the assistance of the Information Sciences Institute (ISI) at the University of Southern California (USC) in Los Angeles. an Iraqi immigrant posing as a civilian being questioned by a U. however." Google's Peter Norvig on managing the data deluge.New system can recognize words.. soldier. director the SRI lab that developed the two-way translation system called IraqComm. [Go to the related podcast to hear the actual conversation." • Also see: August 23.... Last month.] . 2006). Saad Alabbodi.. says Precoda. medical personnel. software performs the translation. . San Francisco Chronicle & SFGate. [F]or more complicated sentences. Technology Review (August 23. and Iraqi citizens struggle to convey crucial information on a daily basis. There was another pause as the computer translated Alabbodi's reply into English in a mock interrogation that provided another example of how technology is slowly mimicking complex human capabilities such as speech.. understand simple foreign phrases. answered in his native tongue. By Kate Greene. . converts simple English commands into Iraqi Arabic or 15 other languages. . The software consists of two components. explains [Kristin] Precoda. computer scientist Harry Bratt spoke into the microphone of his lab's new translation computer: 'Did you hear the explosion this morning?' Several seconds later. the translation software turns to a type of algorithm that performs a kind of statistical analysis on the language. facilitates an English-Arabic conversation by recording a person's spoken words. Peter Norvig explores what .S. Soldiers.' said Kristin Precoda. Unlike human translators. "Researchers in computational linguistics and information retrieval now have a million times more data than was available 30 years ago. called IraqComm." Military getting high-tech help from SRI lab . 2006). then. "Overcoming language barriers can be a matter of life or death in Iraq.already in use in other parts of the world. 'One of the crying needs in Iraq is overcoming the language barrier. Ultimately.. Video of talk delivered on September 25. While human translators are used in many situations. 2006 at UC Berkeley as part of the CITRIS Distinguished Speaker Series. emphasizes SRI's Precoda.this time in the Iraqi dialect of Arabic.

' Getting machines to understand both spoken and written language has been an elusive goal for the tech industry for many years.. information extraction. PC Magazine (July 13. . Germany and Carnegie Mellon University.Inching toward Human Quality." Machine Translation .CNET News. Scaling the Language Barrier. The aim of the book is to introduce this topic to the general reader --. R.com(August 22. Pittsburgh. .anyone interested in human language.machine translation might be ready to compete with human translators. 21(2): 4-6). or Machine Translation (MT) as it is generally known --. "After 50 years of research and tinkering. • Also see John Hutchins' Machine Translation website for additional resources such as: o his collection of "[a]rticles. interACT. books and papers about machine translation and computer-based translation tools. and example-based MT (EBMT). 2005).. one of the most famous anecdotes is about asking a speech recognition engine. An overview of machine translation." • Also see this related news article: Google dominates in machine translation tests. IEEE Intelligent Systems (March/April 2006. Karlsruhe." • See these related news articles. "In the annals of computer comedy. MT requires complex cognitive operations to perform a seemingly mundane task: decoding a source text and recoding into the target language. USA. or part of the process of translating from one human language to another.. translation. Lorna Balkan. and extrapolates to what more data may bring in the future.By Michael Kanellos. "In the News" article by Jan Krikke. Several companies have announced breakthroughs or substantial progress in MT research in recent months.Lee Humphreys and Louisa Sadler (1994). by John Hutchins (University of East Anglia. By Doug Arnold. machine translation (and understanding) of written language is getting unfunnier by the minute. is a joint center between the Universität (TH). thanks to a wave of government funding and technical breakthroughs." "The international center for Advanced Communication Technologies. 2004). [statistical machine] translation. and inference. statistical MT(SMT). Now." Machine Translation: An Introductory Guide. Siety Meijer. The three common methods are rule-based MT(RBMT). "The topic of the book is the art or science of Automatic Translation.the attempt to automate all. or computers. 'Recognize speech?' The translation comes back: 'Wreck a nice beach.. The one clue . United Kingdom: updated January 2005). the historical development and current use of computers for the translation of natural languages. By Sebastian Rupley.this data can do for problems in language understanding. is available from the British Computer Society'sNatural Language Translation Specialist Group.

"The goal of the Speech-to-Speech Translation (S2S) research is to enable real-time... tested in Papero robots and then put in PDAs.000 English travel and tourism related words. Due to end in February. interpersonal communication via natural spoken language for people who do not share a common language. and Text-to-Speech Synthesis (TTS).. The Multilingual Automatic Speech-to-Speech Translator (MASTOR) system is the first S2S system that allows for bidirectional (English-Mandarin) free-form speech input and output. rather than just translating one word at a time. the better. Papero (Partner-Type Personal Robot). Natural Language Understanding (NLU). Carnegie Mellon University." Links to publications and additional information appear at the bottom of their page." Computer aid ensures speedy. in other words.. It is technically extremely difficult because of the need to integrate a set of complex technologies – Automatic Speech Recognition (ASR). It can cope...the more you say... IBM Research.The research leading to MASTOR was initiated in 2001 as an IBM adventurous research project and was also selected to be funded by the Defense Advanced Research Projects Agency (DARPA) CAST program (formerly called 'Babylon' program). with slang and local chatter. Robo-talk helps pocket translator.000 Japanese and 25. Construction of robust systems for speech-to-speech translation to facilitate cross-lingual oral communication has been the dream of speech and natural language researchers for decades. 2004). While both techniques have . By Gregory M. As well as being able to understand and imitate human behaviour. The speech-to-speech technology was developed by NEC. That allows it to discern whether the word baseball in a given phrase refers to a ball or a game. Microsoft is primarily focused on extracting meaning from documents in English. Machine Translation (MT). the University of Southern California. the 36-month IST programme project has drawn on two of the most commonly used translation technologies developed to date: Computer-Assisted Translation (CAT)." Speech-to-Speech Translation." E-translators . IST Results (January 12. "Universal translation is one of 10 emerging technologies that will affect our lives and work 'in revolutionary ways' within a decade. high-quality translations. in which human translators work in unison with a computer.. BBC News (March 4. in which the computer handles the entire process. .Meaningful Machines has given about its software is that it will use new methods of statistically ranking the likelihood of what entire phrases mean. and Microsoft Research operate some of the largest programs for developing machine translation software. Technology Review says. "Increasing translators' productivity is the goal of TransType2. and has a vocabulary of 50. 2004). is the first robot to translate verbally between two languages in colloquial tongue. "Visitors landing at Tokyo's Narita Airport will be able to hire a device which can translate the local lingo. . By Jo Twist. . an innovative computeraided system that allows rapid and efficient high quality translations. Natural Language Generation (NLG). 2005). and Machine Translation (MT). Lamb. The Christian Science Monitor (April 22.

developed by Kevin Knight and Daniel Marcu at the Information Sciences Institute. NewScientist.often with mixed results. Most existing translation software uses hand-coded rules for transposing words and phrases. [Professor Wolfgang] developed the 'Verbmobile'. First." Software learns to translate by reading up.' says IDC analyst Steve McClure. example-based systems. However. DW-WORLD.. The pair founded a company called Language Weaver in Los Angeles. takes a statistical approach... 2005). relies chiefly on raw computing power. This is essentially a computer that translates between German. Knowledge-based machine translation. By Will Knight..." Another Step Closer to Artificial Intelligence. to sell the software as an automated translation tool. a rules engine parses the original sentence. part of the University of Southern California. prepositions. ." You can translate text of your choice by using free translators such as these from: . Technology Review (June 2003).' Computer-assisted translation typically involves two steps. phrases and syntactic structures.advantages and drawbacks. 2001) "This year's prestigious German Future Prize has been awarded to the inventor of an electronic translating device which brings humanity one step closer to the concept of Artificial Intelligence." • Find out more about the Verbmobil at the German Research Center for Artificial Intelligence (DFKI GmbH). "Translation software that develops an understanding of languages by scanning through thousands of previously translated documents has been released by US researchers." By Alan Leo. (December 1. By Chip Walter. building probabilistic rules about words. "'This whole area of language is extremely complex. and so on for each language. The World Wide Translator." • Visit Language Weaver's web site.. Will Web-wide "translation memory" finally make machine translation pay off? "Hour is the moment for all the good men to come to the subsidy of them country. But the new software. A second approach. US. 'It's probably the most complicated problem in computer science that I'm aware of.com news service (February 22. English and Japanese. . for example. "Researchers are making progress today using three basic approaches drawn from natural-language processing. The engine then translates each word within the context that it believes to be correct-. nouns. MIT Technology Review (September 21. US.DE. 2001). this strategy selects the most likely translation using sophisticated mathematical models that the software continually upgrades based on how often its interpretations prove accurate. Statistical techniques also depend on computing power to compare reams of previously translated text. attempting to identify the relationships between the words. TransType2 has 'used the best of both worlds' says project manager José Esteban at Atos Origin in Spain. relies on human programmers to write lists of rules that describe all possible relationships between verbs. The Translation Challenge. .

. our team of deaf and hearing researchers is working towards the realization of a digital English-to-ASL translator. • • Computer Program Translates Spoken English Into Sign Language.. AScribe Newswire / available from National Geographic (August 12. as part of IBM's premier global student intern programme. The Associated Press. 80 of the most talented students from across Europe were selected to work on 20 projects and given whatever equipment. which SiSi then interprets into gestures. By Liz Austin. In the European part of the programme." Visit their site and meet "Paula. But it's even harder if you're deaf. they focused on innovative technology projects. all of which had real business value.. The computer processes the command. This project is an example of IBM's collaboration with non-commercial organisations on worthy social and business projects. ." a virtual interpreter. Working for an intense 12 week period alongside IBM technical and industry leaders. "Paula is a computer-generated synthetic interpreter developed by a team of faculty and students in the School of Computer Science. SiSi has been developed in the UK by a research team at IBM Hursley. Telecommunications and Information Systems at DePaul University in Chicago.. The system works like this: A hearing person speaks through a headset.AltaVista Applied Language SDL International GOOGLE InterTran SYSTRAN IBM Research Demonstrates Innovative 'Speech to Sign Language' Translation System. "IBM (NYSE: IBM) has developed an ingenious system called SiSi (Say It Sign It) that automatically converts the spoken word into British Sign Language (BSL) which is then signed by an animated digital character or avatar.. "Navigating airport security is stressful for anyone these days. The signing avatars and the award-winning technology for animating sign language from a special gesture notation were developed by the University of East Anglia and the database of signs was developed by RNID (Royal National Institute for Deaf People). SiSi brings together a number of computer technologies. visit the following url: http://youtube. (September 13." Animated interpreter translates spoken English into sign language for travelers. Extreme Blue. . support and assistance they required.. which is connected to the computer. and the animated figure of Paula translates the message into ASL through hand gestures and facial expressions on the computer screen. "Combining computer technology and linguistics research to bridge the communication gap between the deaf and hearing worlds. A speech recognition module converts the spoken word into text.com/watch?v=RarMKnjqzZU" The DePaul University American Sign Language (ASL) Synthesizer.. that are used to animate an avatar which signs in BSL. 2002). such as SiSi. Computer scientists from DePaul University believe they have a solution: a 3-D animated interpreter that . IBM press release via Market Wire. . 2007). .. For a video demonstration of the SiSi technology.

Combine that with the millions throughout the world who would also benefit.' says graduate student Sunny Srinirasan.Recognising Auslan signs using Instrumented Gloves. 2005 press release) and TESSA & VANESSA. Speech Technology Magazine (September/October 2003)." • • • Machine Translation's Past and Future.. Here's where you'll find Guido. configurations and facial expressions that make up ASL.'" Speech. "Using digital avatars as signing translators could significantly expand the ways deaf and hard of hearing people communicate with the hearing world. A computer program takes spoken English and converts it in real-time to text. By Jon Wurtzel. and not just because it is the right thing to do." I See What You Are Saying. 'It’s really a machine-translation project where the translation is from sounds to hand movements and positions. 'This involves transforming verbal communication into an animated visual format.American Sign Language (ASL). And also see the rest of the translation related articles in this issue of Wired. the team has created 'Paula'" an animated figure that translates simple sentences into the hand and body positions. Compiled by Carl Zimmer. By Steve Silberman. By Dr. The deaf and hard of hearing account for 8. Language & Virtual Human Research at the School of Computing Sciences. Businesses should pursue this technology. and a huge market opportunity emerges for the right products. School of Computer Science and Engineering at the University of New South Wales.• can translate spoken English into American Sign Language. Judith Markowitz. 8.. . 2002). The avatars are computer animations designed to look and move like real people." • Find out more about this field on our Assistive Technologies page. . "A renewed international effort is gearing up to design computers and software that smash language barriers and create a borderless global marketplace. Using speech recognition and animation software. but I have to warn you that it's a little out of date." Digital characters 'talk' to the deaf.. Waleed Kadous' Honour Thesis (1995). Wired (May 2000. GRASP . "You may also be interested in my Machine Gesture and Sign Language Recognition page. BBC (March 2. The digital avatars then take this English text and sign its meaning on a display screen. a "virtual signer" (see this May 5. University of East Anglia.05). The goal of the DePaul researchers is to capture spoken instructions and convert them into the fourth most widely-used language in the United States -.. . Talking to Strangers.A look at the hubs for machine translation R&D worldwide. A timeline from Wired covering the span from 1629 through the year 2264! Compiled by Kristin Demos and Mark Frauenfelder. Universal Translators . "Theres no doubt that speech recognition is an assistive technology.6 million of the 59 million people in the UK. in effect becoming a translator between spoken English and British sign language.

solemnly consults a phrase book.84). commercial system developers. By Kevin Knight. by David O. No.Lost in Translation. Woodbury. Like many AI tasks." Automating Knowledge Acquisition for Machine Translation. "Machine translation of human languages (for example. evaluating. 2. and information retrieval. "AMTA is an association dedicated to anyone interested in the translation of languages using computers in some way. with a primary focus on machine translation.) "The Center for Machine Translation (CMT) is a research branch of the School of Computer Science [at Carnegie Mellon University] devoted to basic and applied research in all aspects of natural language processing." • Be sure to check out their current research such as DIPLOMAT (Distributed Intelligent Processing of Language for Operational Machine Aided Translation) and the Lockheed-Martin-led Tongues project. "In one famous episode in the British comedy series Monty Python a foreign-looking tourist clad in an outmoded leather trenchcoat appears at the entrance to a London shop.." • Also see this article from the August 1959 issue of The Atlantic Monthly: The Translating Machine. pages 60 . sponsors. English. AMTA has members in Canada. and the United States. and understanding the science of machine translation (MT) and educating the public on important scientific techniques and principles involved. It is the regional component of a worldwide network headed by the International Association for Machine Translation (IAMT). This is not so fantastic as it sounds. This includes people with translation needs.. Japanese. AI Magazine. researchers. Spanish) was one of the earliest goals of computer science research. 6. translation requires an immense amount of knowledge about language and the world. Containing a unique mix of academic and industrial researchers specializing in various aspects of computer science.. 81-96. Association for Machine Translation in the Americas. and in a thick Middle European accent declares. and people studying.. 18(4): Winter 1997. He would like to have a machine that will translate material that is merely spoken to it. 'My hovercraft . He marches up to the man behind the counter. The Atlantic Monthly (December 1998 / Volume 282.. is not going to be satisfied even with this kind of short cut. No. such software can now easily be run on a personal computer. which packs the power of a mainframe into a desktop." . This episode is brought to mind by some recently available computer programs that claim to provide automatic translation between English and a number of other languages. By Stephen Budiansky.. computational linguistics and theoretical linguistics. pages 80 . is full of eels!' ." (Volume 204. but with the advent of the Pentium chip.64. This article illustrates these approaches. speech processing.. "Professor William N. Recent approaches to machine translation frequently make use of text-based learning algorithms to fully or partially automate the acquisition of knowledge. head of MIT's modern languages department and a prime mover in machine translation.. Latin America. . artificial intelligence. and it remains an elusive one. Translation software that runs on mainframe computers has been used by government agencies for several decades.. Locke.

and linguistics. Abstract Real-time strategy is one of the most important game genre from the beginning of the computer games history and one of the biggest inner market in computer games market. 1. long term decision making in strategy games. Simply if the player that he wants to guard is tall and plays very slow relative to him then . determining correct buildings to build." Language Translation (TRL) at IBM. attacking to correct enemy troops. "This project deals with natural language analysis and translation by computer. Definition of Fuzzy Logic The best definition of fuzzy logic is given by its inventor Lotfi Zadeh. if a player wants to guard another player firstly he should consider how tall he is and how his playing skills are. such as syntactic parsing and word sense disambiguation. resource management. Key Words: Artificial intelligence in real-time strategy games. "A semantic network or net is a graphic notation for representing knowledge in patterns of interconnected nodes and arcs. Age of Empires." • Also see this December 2004 article from AI in the news. Semantic Networks. determination of attacking or fleeing.Some DARPA projects: • • • One-way Phrase Translation System (PTS) Phraselator also see the National Institute of Standards and Technology's Machine Translation Benchmark Test and the 2005 results. This paper will try to improve real-time strategy games’ AI by improving long term decisions such as.” The meaning of solving problems with computers akin to the way human solve can easily be explained with a simple example from a basketball game. By John Sowa. Technologies used for machine translation. Also this paper will try to give examples from strategy games such as Command and Conquer: Tiberium Wars. neural networks. in spite of that fact there are only a few strategy games have successful AIs. short term decision making in strategy games. fuzzy logic. creating correct troops against opponents’ troops. psychology. are commonly used for other applications of natural language processing. but earlier versions have long been used in philosophy. Computer implementations of semantic networks were first developed for artificial intelligence and machine translation. achieving correct upgrades/technologies with neural networks as well as to short term decisions such as. “Fuzzy logic means of representing problems to computers in a way akin to the way human solve them and the essence of fuzzy logic is that everything is a matter of degree.

• • • • if player is short but not fast then guard. These steps are. In this example the important point is the properties are relative to the player and there is a degree for the height and playing skill for the rival player.87 meters which is quite tall relative to our player and can dripple with 3 m/s which is slow relative to our player.192) To exemplify the fuzzy procee steps. Addition to these data some rules are needed to consider which are called fuzzy rules such as.he will use his instinct to determine to consider if he should guard that player as there is an uncertainty for him. if player is fast but not short then don’t guard If player is tall then don’t guard If player is average tall and average fast guard . firstly fuzzification where crisp inputs get converted to fuzzy inputs secondly these inputs get processed with fuzzy rules to create fuzzy output and lastly defuzzification which results with degree of result as in fuzzy logic there can be more than one result with different degrees. Bourg P. As mentioned in the example the rival player is tall with 1. the previous basketball game situation could be used. Figure 1 – Fuzzy Process Steps (David M. Fuzzy logic provides a deterministic way for this uncertain situation. There are some steps to process the fuzzy logic (Figure-1).

7 + 0.5 . 2004) Figure 5. is using for creating a crisp output which is a number which may determine the energy that we should use to guard the player during game.204) Output = [0.2 * 10] / (0.4 + 0.2. the degree for guard is 0. (David M.2) ≈ -3. Bourg P. degree for sometimes guard is 0. defuzzication. The centre of mass is a common method to create the output.4 and never guard is 0.fuzzy output (David M. Figure 4-output fuzzy sets On the last step.7.Figure 2 – how tall Figure 3.4 * 1 + 0.how fast According to the rules and the input data an output will be created by fuzzy system such as.7 * (-10) + 0. Bourg. On this application it is considered to give high weight to guard or not guard but low weight given to sometimes guard. On this phase the weights to calculate the mean point is totally depends on the implementation.

Figure 6. a processing unit named cell body and an output unit named axon. determined by the connections between the processing elements and element parameters” (Wikipedia. The structure of ANN (Artificial Neural Networks) is same with human’s neural network’s structure as in human neural system there are receptors to collect the data named dendrites.As a result fuzzy logic is using under uncertainty to make a decision and to find out the degree of decision. Artificial neural network). there is a mathematical background which makes this logic work for computers. The problem of fuzzy logic is as the number of inputs increase the number of rules increase exponential. 2005). Definition of Artificial Neural Networks Although there is no agreed definition the most common definition is “it involves a network of simple processing elements (neurons). On this part of this . Similar to this structure in ANN there is an input layer. p. This method which is called back propagation is a supervised learning. training sets for feeding the ANN may not have all the possibilities or these sets may contain novel data (Dr Emma Hart. 2002. The problems of that method are.241) As seen in the figure the output will depend on the inputs and the weights as well. On reverse order if we know have the inputs and if we know the results for every input pair than we can calculate the weights therefore after finding weights if we give input values to our neural network it can calculate the correct output for certain input pairs. 2. Although the logic sounds pretty easy for ANNs with supervised learning.structure of a simple neuron (Mat Buckland. which can exhibit complex global behaviour. a processing unit which sums the inputs after multiplying them with weights and an output layer which gives a result for a neuron (Figure 6). This is the main point of the ANN as if we can find the correct weights for the inputs than we can create a correct result for ever situation.

choosing correct number of hidden layers and hard debugging. Real Time Strategy Games (RTS Games) A RTS game is a strategic game which runs in real time distinguish it from turn based strategy games. 3. there are different estimations for that problem such as square root of number of input layers multiply by number of output layer. ANNs are using for complicated or imprecise data and also for recognising the patterns (Christos Stergiou. p. choosing correct propagation sets. Increasing number of hidden layers increases the precision and complexity of the calculations which results with accurate calculations with using more CPU time and more memory that is the trade off. This means that for complex calculations the hidden layer is obviously necessary. NEURAL NETWORKS). one hidden layer and one output layer (Mat Buckland. high consumption of resources. A neural network without hidden layer can make logical calculations such as ‘AND’ and ‘OR’ but cannot calculate XOR operation. The number of neurons in the hidden layer is up to implementation. (To get more information about ANNs please check further reading) Figure 7. To find the best number of hidden layers the only way is experimenting different values. Although the high number of RTS games there are only a few scenarios . In brief. 2002. however. Recognition of patterns requires very complicated methods and data structures with classic methods.242) As seen in the figure above there is a hidden layer which is necessary to make complex calculations.structure of a neural network with one input layer.paper no mathematical background will be explained since it is not the main goal of this paper. The cons of ANNs with back propagation supervised learning are. however ANNs are very simple structures which make the implementation easier as ANNs are selforganising structures as well.

like choosing correct technologies to achieve. Although there is a static hierarchical order for creation of units or achievement of technologies. If the decision is unit wise such as choosing the correct troop in the range to attack will be called as short term decision. This makes the game AI dummy since if the human player creates a trap with a wall such as builds a wall around an archer. On the other hand to upgrade the unit strength usually players should achieve new technologies which are usually much costly than unit production. In the history of RTS games. On the other hand the decisions.are used for these games. To give an example AOE-2 (Age of Empires II) has a rule based AI with priority queues which means nearly static development for NPC (non player character). That makes the AI very complicated. To give an example all the troops choose the enemy with lowest health in their range but this approach still involves some problems. The buildings usually enable new unit tapes. which are not individual decision for a troop but about a certain group of all troops in the game or the decisions which will affect the destiny of the game for long term will be called long term decisions. To find alternative solutions for these problems in this paper the decisions will be divided into two parts according to their importance. To give an example the player can create knights by using stable and to build a stable a barracks should have been built. the troops behave reasonable as they can choose the correct troop to attack according to its health. The player should use the villagers to collect resources and create new buildings or units who can be soldiers or villagers. That’s because of their static structure and behaviours. Moreover this game has obviously problem while making long term decisions because NPC obviously cheats by having lots of recourses and by producing them very fast. As seen in this scenario usually in RTS games there is a hierarchical order which the player should follow to defeat the enemy. Thankfully in new generation games such as Command Conqueror Tiberium Wars. game AIs usually statically programmed like finite state machines for decision making. Besides these long term decision failures in AOE-2 consideration mechanism for choosing the correct the enemy to attack is not working at all as the troops always choose and attack an enemy until they die. If the player can find a way to defeat the NPC than the player will never lose again as the NPC cannot evolve itself and cannot find a way to overcome the bottlenecks of its management strategy. Moreover the only problem in RTS games is not decision making but also path finding or this kind of AI algorithms but in this paper only decision making will be discussed. he has to write lots of scripts as there is no rule to generalise in this situation. all the knights try to attack this archer but they are not able to attack because of the wall but they lose lots of energy or time. and a few resources. Even if the AI programmer can find out this bug and tries to prevent this situation. . These approaches make strategy games very boring for game players as if the game player can defeat NPC for once then computer nearly has no chance to win again. always complex algorithms running for RTS games AI since the number of probabilities and parameters are very high for making decisions. The most popular scenario starts with a couple of productive units such as villagers.

short term decision means instantaneous decisions made by individual troops or the controlling mechanism such as. However the resource management cannot be done by analysing some parameters because of the huge amount of the parameters and complex relations between these parameters. a. Unlike some of the RTS games. The short term decisions such as considering the correct troop to build is a less complex decision compare to resource management and it is only uncertain which means can be found out by analysing some other parameters. Armour Attack Power Attack Speed Movement Speed And the parameters are found by some calculations using the variable above. Attack power of troop against the enemy. The sections below based on a hypothetical RTS game scenario.100]. This means that while the first troop causes 50×1 = 50 units of damage in T seconds but the second troop causes 15×4 = 60 units of damage which means the second troop is stronger than second one. Although these kind of short term decisions are unpredictable. 100 represents the healthiest and 0 is death. In the next parts of this paper. . the other troop has the attack power of 15 with the speed of 4. In this hypothetical RTS game the units have the properties showed on the list below with explanations. in this example there is only one type of armour for the troop which reduces the attack power of enemy against the troop. these short term decisions will be discussed in terms of their input data. Attack speed is the variable defines how many time can the troop attack to the enemy in a constant time interval Differs from attack speed.Not only the importance but also the complexity of the decisions is another reason for this differentiation. Health The health of the troop. To give an example. let’s assume there is two kinds of troops first one with attack power of 50 and attack speed of 1. The main reason for doing that is having more realistic information. Short Term Decisions in Real Time Strategy Games As mentioned before. it is constant for every type of the troops. output data and the way to make these decisions with the explanations. decision of attacking or fleeing or creating the correct troops according to immediate data. this is the parameter to define how fast the troop move or escape. in fuzzy set it will be normalized range between [0. they can be made by deterministic calculations such as Fuzzy Logic which provides a high resolution for output with crisp input data.

= The mean of the speeds of the enemy troops attacking to the troop. on the other side Team B has five troops and all of them heavily injured but has the opportunity to destroy the enemy troop.Relative Attack Power OAS = Own Attack Speed EAS = Enemy’s Attack Speed = Sum of the powers of the troops attacking to the target troop = The target troop’s armour = Sum of the powers of the enemy troops attacking to the troop = Enemy troop’s armour in the aim of the troop = The troop’s Armour. The result of 50 means equality. This variable normalized by multiplying with 50. The result of 50 means equality. This variable normalized by multiplying with 50. To give an example. Relative Speed = Own Movement Speed = Enemy’s Movement Speed = The mean of the speeds of the attacking troop’s to the target troop. if the Team A has only one troop with good condition in terms of its health. On this condition if the consideration algorithm . The usage of symbol adds the group behaviour for the decision making.

Attack or Flee In a RTS game one of the most usual decisions to be made is the individual decision of a troop to continue attacking or start fleeing. On this condition RAP (Relative Attack Power) of number 7 will be calculated by sum of powers of number 7 and number 8 divide by the attacking power of number 3. On the other hand number 7 is being attacked by number 3. So the equation for RAP is. warcraft. command conqueror as well as age of empires these kinds of decisions made by FSM (finite state machines).runs on only the troops one by one than all the Team B troops should escape from the clash but actually they shouldn’t since they can destroy the enemy. Apart from FSMs another approach can be the Fuzzy logic which provides realistic behaviour but consumes more CPU time but this is a trade off and acceptable due to the increasing CPU/GPU power. In most of the RTS games like. dune 2000. The troop with number 7 from the Square Team is attacking to the troop with number 2 from the Circle Team and the number 2 is being attacked by number 8 as well. . The main reason for these games to use finite state machines can be predict as reducing the CPU time for game AI as FSM is a static structure which needs minimum amount of resources but the problem of this structure is the number of states and unrealistic behaviour. Another example for better understanding can be given from the figure below. Equation 1 – RAP Equation for Troop 7 Figure 8 – A clash example between two forces i.

The first stage to setup the fuzzy logic is determination of Fuzzy Input data Sets (FIS) and membership functions. Relative Movement Speed (RMS). second one is Flee (figure-9). . Enemy’s Health. On this paper only linear membership functions such as triangle and trapezoid used for easy understanding as well as easier calculation. Own Health Near dead Injured Normal Enemy’s Health Near dead Injured Normal RAP Weak Equal Strong RMS Slow Equal Fast Table 1 – Fuzzy Input Sets And the third step is defining these FIS’s membership functions. first one is Attack. With the help of these variables the troop will show the group behaviour and make realistic decisions. however it is better to use logarithmic curves for RAP and RMS since they are the results of division of two forces and two speeds. The other step is determination of membership function. Figure 9 – Fuzzy output sets and member functions The FISs are Own Health. For both of these data sets 50 represents the Equality. However it’s better to define the Fuzzy Output Set (FOS) and its membership functions as we have only two FOSs. Relative Attack Power (RAP).

equality is 50 and definitely stronger means 1. The figure below shows the RAP membership function. As seen in figure.6.Figure 10 – Membership function for Own Health / Enemy’s Health which are normalized to 100 The figure above shows the membership function for Own Health as well as Enemy’s Health. Figure 11 – RAP Membership function . The main reason for doing that is to prevent all the troops escape from the battle as all the troops should definitely fight if they are over 30 and they should try to escape if they are near dead.2 times stronger than the troop which is equal to 60 and definitely weaker means 1. the health under 10 is definitely named like near dead and over 30 counts like Normal.2 time weaker than the troop which is equal to 46. In this MF (membership function).

This part is the most important and most open part to make mistakes. In addition. If the tolerance is kept 20% than the flee consideration may not work as fifteen percent slower means no way to escape so it is better to keep the tolerance at 10%.1 times faster means definitely faster and 1.1 times slower means definitely slower. the numbers of all combinations are. However it is not necessary to create all the rules for every possibility.Figure 12 – RMS Membership function On the other hand 1. In our system the rules are. 3×3x3×3=81 INPUTS Own Health Enemy’s Health RAP Not near dead All possibilities All possibilities near dead near dead near dead near dead near dead near dead near dead near dead OUTPUT Attack / Flee Attack Attack Attack Flee Flee Flee Flee Flee Flee RMS All possibilities All possibilities All possibilities Slower injured equal Not faster near dead Weaker Not slower injured Weaker Not slower normal Weaker Not slower normal equal faster normal stronger faster injured equal faster Table 2 – Fuzzy Conditions for Attack or Flee If the troop is not heavily injured (not near dead) then it should continue attacking and shouldn’t escape. And the last part is determination of rules. The problem is if it is near dead since all the flee possibilities needs this . The tolerance is 10% to prevent the errors.

38(near dead) 35.38(near dead) 36.8(stronger) 9. RMS 53. But even if the troop is near dead and slower than the enemy it should attack because there is no way to escape and the rest of the rules are easy to understand with the help of the table above.8(stronger) Table 3 – Test decisions Although the only difference is enemy’s health with the difference of 1.condition first.1(faster) 53. One of the best examples is giving these values.1(faster) 53. And the next turn if the troop got closer to death than will definitely escape showed at the last line of the table above. troop will definitely attack.9(normal) 56.6(normal) 56.6(normal) 56. And the very last part is testing the fuzzy system with different data.3 the result changes and seems to be a good decision since if the enemy is weaker than there is a possibility to kill because it is stronger.38(near dead) 35.1 . Own Health Enemy’s Health RAP 9.8(stronger) 8. All the data should start with the near dead condition or injured for Own Health since for the condition of normal.1(faster) Result Attack Flee Flee Figure 13 – Decision is attack with the value of 51.

6 ii. The FIS terms and the explanations for the hypothetical game scenario of this section are. Fuzzy Logic will be used to answer this question. In this situation this troop should choose it according to degree of weakness of the enemy and this weakness should be calculated with the help of these troops’ properties. OAP = Own Attack Power Own Effective Attack Power (OEAP) OAS = Own Attack Speed EAR = Enemy’s Armour EFH = Enemy’s Full Health EAP = Enemy’s Attack Power Enemy’s Effective Attack Power (EEAP) EAS = Enemy’s Attack Speed OAR = Own Armour OFH = Own Full Health . This explanation seems best fit to Fuzzy Logic to be used for determination.Figure 14 . The main reason for using Fuzzy Logic is the problem involves uncertainty and the solution should be deterministic. This decision also is a short term decision since it is only related with an individual troop also in this part of this essay. health attack. power as well as armour. Choosing Correct Troop to Attack Another short term decision for individual troops in the RTS games is choosing correct troop to attack. To give an example during a clash between two enemy groups let’s assume that Team 1 has one troop and Team 2 has two troops and the troop in team 1 trying to determine which enemy troop to attack also let’s assume that for each troop number of properties are three such as.Decision is flee with the value of 49.

. These equations differ from the equations in `Attack or Flee` section of this essay since while determining the correct troop to attack should be done according to individual attack power not group attack power.ECH = Enemy’s Current Health Enemy’s Health (EH) EFH = Enemy’s Full Health This variable normalized between [0-100] where 100 is healthiest. The main reason for doing that is. if the group power is calculated instead of individual power against an enemy troop we cannot really choose a weak enemy for our attacking skills. After choosing FISs second part is creating the MF for these FISs. Another interesting point for this approach is this part doesn’t include Own Health parameter since this section is not determining our attacking or fleeing decision this means that the decision of the troop should be best fitting decision for the weakness degree not our own health.

The next step for creating our fuzzy logic is creating the output (FOS). OEAP strong strong not weak weak Inputs EH not healthy healthy near dead near dead EEAP All conditions All conditions not weak weak Output attack neutral attack neutral . there are 36 possible combinations however it is reduced by using not operations as a result there are 15 combinations to implement.Figure 15 – Membership functions for Choosing Correct Troop to Attack Different from the ‘Attack or Flee’ section. In this section. these are. The output membership graph consists of three possibilities as we need a precise output for this short term decision. And the third step is creating rules. The mean reason of putting the healthy parameter is increasing the precise for enemy’s health MF since it is really important for the decision calculation. there are four MFs where healthy MF is new.

But the fuzzy logic has an answer for both of the troops. however. the troop is powerful against the troop 1 and health of troop 1 is bad but better than troop 2.Fuzzy rules for choosing correct troop to attack The main goal of these rules is attacking to the weakest in terms of its health and our attack power against this troop as well as the strongest enemy in terms of its attack power. . So it is hard to determine since troop 2 is closer to dead but our attack power is not as strong as against troop1. After creating out fuzzy system the troop can choose the weakest enemy after the defuzzication operation.not weak weak normal weak normal normal weak weak not weak weak injured injured healthy healthy normal normal normal not near dead All conditions All conditions All conditions All conditions All conditions All conditions strong not strong All conditions All conditions strong strong attack attack neutral don’t attack attack neutral don’t attack neutral attack neutral Table 4. Figure 16.Example for which troop to attack decision To give an example. first and second are from Circle Team and the third one is from Square Team (Figure 16). And the variables for the troop 3 against 2 and one are. Troop 1 EH 19 Troop 2 EH 7 OEAP 88 EEAP 88 OEAP 55 EEAP 95 Under these conditions. let’s suppose that there are three troops. troops 2’s effective attack power is better than troop 1.

So the troop will attack to troop 2 as the output is bigger than troop 1’s output.Output (result of defuzzication) Troop 1 66. Long Term Decisions in RTS Games .Outputs for troop 1 Figure 18. Figure 17.7 Troop 2 67 Also the results of the fuzzy logic are very close to each other as expected but there is a numerical result that we can decide according to.Outputs for troop 2 b.

This causes very static game scenario since the human player finds a way to repel the CCP and after the human player cannot be defeated by the CCP because the CCP cannot create any new way. For RTS games long term decisions are vital since the CCP (computer controlled player) should behave realistic. at the end of the seventh minute CCP attacks with a constant number of troops. Therefore to create a strong opponent against the human player they prefer using cheating methods such as gifting new troops as well as resources which frustrates the human player. To create a realistic behaviour for CCPs. at the end of the fourth minute. achieving correct upgrades/technologies. . determining correct buildings to build. This section of this paper will recommend using ANN (artificial neural networks) for long term decision making by giving some basic ideas such as defining input layer parameters for ANN and the outputs as well. Every time the game player experiences the same game for the same map. harvesters) should be created and ordered to collect certain types of resources.The easiest explanation for long term decisions in RTS games can be described as the decisions which affect all or a group of troops or buildings for a long time as well as can be considered as the management strategy of the game player. this method consumes lots of CPU time and provides a very slow learning. In addition to resource managements other examples for long term decisions are. However. four villagers hunt deer. Even if the numbers of possibilities are certain then possibilities and parameters are too much to make an easy decision. The most common method for making these kinds of decisions are again the finite state machines which cause nearly a static game play. To give an example in AOE2. which means intelligent and learnable behaviour. orders them in a static way such as. ten of them collect food from trees etc. the CCP sends a scout to explore the map and creates a static number of villagers. all the recommendations are hypothetical since none of the ideas are based on any calculations or experiment. The game producers of these RTS games usually create an AI with a static behaviour by using scripting languages. intelligent as well as shouldn’t to not to frustrate the human player. For these hypothetical recommendations the famous RTS game AOE2 (Age of Empires 2) will be used as the RTS game environment. However. villagers.g. The best example for long term decisions is resource management during game play which means how many resource collectors (e.. choosing correct time to attack with full power etc. ANNs may also provide un-deterministic behaviour by integrating GA (Genetic Algorithm). Not only for RTS games but also for any kind of game long term decision making always a big problem as the number of possibilities is may not be a certain value. Moreover the difference between a short term decision and a long term decision is simply unreasonable short term decisions can be fixed in a short time however long term decision cannot be fixed so easily. In addition to this ability of ANNs. some other methods should be used such as ANN since it provides learning for CCPs.

the module approach is preferred to be used. the training method for the RTS AI is back propagation which is a supervised learning method and the weight calculations are not dynamic. weights and outputs. However.g. behaviour of the CCP during dark-age in terms of resource collection should be different from castle age. Instead of using the current age as an input value for the AI. wood) the player has and the outputs are actions such as. To give an example from our conceptual game AOE2. determination of the criteria should be search carefully to not to train the AI with novel data. an ANN structure consists of three fundamental elements. In our system inputs are the numerical values of a relevant system such as. This means the calculation of weights can be done after the game play. create villager or send a villager to collect gold. Figure 19 – An ANN Module As mentioned before. This also provides parallel calculations for server-side such as calculation of dark. .i.age could be made separately from the calculation of castle age by using threads. To reduce the calculations and to separate behaviours. for resource management system first input can be the recourse (e. gold. creating different ANN modules can be another approach. Another benefit of this approach is the success of each module can be send to server as training data if it fits the necessary criteria such if the player achieves castle age before computer this data can be send to the server even if the player losses the game. ANN Structure and Hypothetic Feeding Mechanism of the ANN As mentioned before on this paper. inputs.

Also the game AI server should contain trained and tested data before release of the game AI since. . no one wants to play with a dummy AI. the client should connect to the AI server and should get the trained ANNs weights to provide a better and dynamic game play. So the game company should be well trained the game AI modules which can be a problem for the game development.Figure 20 – Before games start all weights getting from AI server To load the weights of the game AI. if the player uses a pirate version of the game cannot download the last AI weights since to download the AI data server can request for the player ID and password first. This method can be another approach for reducing piracy in games like.

Calculate until reaching a threshold for every ANN module . For Server Side Weight calculations. Use the previous ANN weights. For every action 1. Collect the action 3. 1. For data collection (collecting the training data). Send all ANN training data sets of the winner’s. join all the data of relevant ANN modules including new data and old data 1. Else don’t mark and don’t discard the ANN training data set 4. Create threads for every ANN module 2. Password 2. mark to be sent to server 3. 1. ii. Check for ID. For AI loading. Collect input variables of the relevant AI module 2. Change the ANN module 2. If the current ANN module reaches the criteria to be changed 1. 1. Connect to AI server 1. 1. i. 2. Send all the marked ANN training data sets. Create the local AI with new weights 4. If cannot connect 1.Figure 21 – At the end of each game all input and outputs sending to AI server for calculation of weights if the result of the game is successful Briefly the steps of this system are. At the end of the game 1. Send weights if successfully connected 3. If there is new data. If the ANN training data reaches the criteria.

Number of workers collecting stone 6. 1. number of troops collecting the resources. Number of workers 2. Create threads for every ANN module 2. Turks etc. In a RTS game for resource management can be the number of resources. Amount of wood we have 7. Example ANN Structure – 1: Resource Management in Dark Age To create the ANN structure first of all the input values should be determined. 1.3. Goths. 1. Amount of wood we have 8. Number of workers collecting food 3. Amount of stone we have 10. Send a villager from food to stone 5. Send a villager from food to wood 3. Amount of gold we have 9. Number of workers collecting gold 5. Race of the side (such as Aztecs. the input values for dark-age can be chosen like. Define threshold values lower than the old threshold values 1.) And the outputs of the ANN module are decisions such as. i. Send a villager from wood to food . For our example game AOE2. If there is no new data. Create villager 2. Number of workers collecting wood 4. Send a villager from food to gold 4. Calculate until reaching a threshold for every ANN module ii. ii.

Send a villager from gold to food 9. however the number of variable makes the fuzzy logic nearly impossible to implement this part and also actually this decision is not only spontaneous but also effects the game in long term as creating of Paladin is as expensive as achieving some technologies. Send a villager from stone to food 12. Send a villager from wood to stone 8. 8. Send a villager from wood to gold 7. At the same time another module is working for achieving technologies and if the resources are enough to pass the next age than all the data should be recorded according to the algorithm mentioned before. Number of enemy’s swordsmen . 5. Send a villager from gold to stone 11. if the player choose a villager from stone collection and send him to wood collection than all the input data and should be collected after the worker starts working. 7. Send a villager from stone to wood 13. The input variables can be. 2. iii. Example ANN Structure – 2: Deciding the Correct Troops to Create This part can be a either fuzzy logic or ANN since it seems like a spontaneous action. 6.6. 3. Send a villager from gold to wood 10. 1. 9. Number of own archers Number of own knights Number of own swordsmen Number of own skirmishers Number of own special troops Number of own other troops Number of own defensive buildings Number of enemy’s archers Number of enemy’s knights 10. Send a villager from stone to gold The data collection in the game should be triggered by the action such as. 4.

Number of enemy’s defensive buildings 15. 1. Amount of gold we have 22. Therefore if this system really can be implemented and reaches a degree of success than game’s lifetime for players definitely will be longer as most of the strategy game players play strategy games for the game AI not only for graphics. 5.11. the numbers of inputs are pretty much since it is really hard to determine even for human instinct which troop to create that makes the game interesting and keeps players’ passions on the game. Number of enemy’s skirmishers 12. For most of the strategy games. increasing income rate providing from resources and other similar ways. Amount of wood we have 20. Own score 17. Number of enemy’s other troops 14. 3. Number of enemy’s special troops 13. Amount of wood we have 21. Conclusion Artificial intelligence is the most important for strategy games and especially for real time strategy games since the computer controlled opponents should make reasonable decisions spontaneously. Create archer Create knight Create swordsman Create skirmisher Create special troop As seen above. game producers preferred the easy way. Score of the enemy (this variable provided by the AOE2 game environment) 16. Amount of stone we have Outputs are decisions again. Enemy’s race 19. cheating in different ways such as giving new troops. 2. Own race 18. however results of these methods never . 4.

2002. Especially choosing correct troop in the range to attack seems to be a successful application of fuzzy logic according to test results but without a real time application it is not reasonable to judge as a successful application of fuzzy logic since CPU usage is not known. the exponentially increasing number of possibilities makes hard the fuzzy logic to be implemented. Another weak point of ANNs is the requirement for huge number of feed data (training). The conceptual distributed server based ANN application hasn’t tried yet by any game. however. Bourg & Glen Seemann. Additionally. As a result. O’Reilly [2] Mat Buckland & Andre LaMothe. is poor. Wordware Publishing Inc. Premier Press [3] Mat Buckland. this trained AI structures can have a commercial value since they can decrease the number of pirate usage as the strategy game players always want to play with a more intelligent opponent and most of them will want to be registered to the AI service provider this means preventing piracy. first of all the CPU intensity of the learning structure. the problems about short term decision making and also long term decision making tried to be solved by using ANNs and Fuzzy Logic but none of the approaches has been tried in a real time game. Actually they can but this method never tried in commercial strategy games. The CPU usage problem of the ANN is a known weak point of this structure. Programming Game AI by Example. On the other hand.satisfied the game players. References [1] David M. AI for Game Developers. in most of the strategy games. This conceptual distributed system may be a key for solution of these problems. . the tested short term decisions seem working. The most important reason for that is. the human player never lose again. July 2004. secondly the success rate is not known as the learning method hardly used in games. Not only machine learning but also spontaneous decision making. Briefly human player can learn but the computer cannot. On the other hand the conceptual ANN distributed system can be a new approach for solving the problems of ANNs in RTS games. There are several reasons behind that. in this paper. the results for fuzzy logic seem to fit like a glove the given problem. 2005. At first sight the implementation of fuzzy logic could be seem like simple especially for the short term decision making. Besides this kind of distributed approach haven’t tried for any kind of game AI yet. Actually these short term decisions can be made with fuzzy logic and in some of the new strategy games it seems to be used (Command Conqueror Tiberium Wars) for choosing correct troop to attack. However. when the human player finds a way to defeat the computer. however it is not definite since no explanation have been made about the game AI for this game. First Edition. AI Techniques for Game Programming. by using the same patterns (tactics).

2002. Michael Buro.pdf.C. last visit date: 30-11-2007 . Strategy Game Programming with DirectX 9. Hierarchical Opponent Models for Real-Time Strategy Games http://www. Computer Games with Intelligence. last visit date: 30-11-2007 [15] Christos Stergiou and Dimitrios Siganos. visit date: 30-11-2007 [11] Daniel Johnson and Janet Wiles.pdf.[4] Todd Barron.wikipedia. http://www.pdf.unimaas.cs.nl/~uiterwyk/Theses/BSc/Jansen_BSc-paper.asp.A. http://en. Fuzzy Logic. http://www. DeLoura (edited by).html#Why%20use %20neural%20networks.uk/~nd/surprise_96/journal/vol4/cs11/report. visit date: 30-11-2007 [10] F. 2007. 2003. Search Algorithms and Neural Networks to Games. Schadd.cs. Wordware Publishing Inc.ualberta.pdf. 13-04-2005. Introduction to Neural Networks. DeLoura (edited by). NEURAL NETWORKS. 2001.0.unimaas.uq. Applying Artificial Intelligence. Monte Carlo Planning in RTS Games. http://en.org/content/2003/KellyMiniPaper. Charles River Media [6] Mark A.itee. June 13 2007.ac.php3? op=getlecture&cloaking=no&lectureid=365774.org/wiki/Artificial_neural_network.soc. http://www. Game Programming Gems 2. visit date: 30-112007 [12] Wikipedia.wikipedia.nl/~uiterwyk/Theses/BSc/Schadd_BSc-paper. Game Programming Gems.ic. last visit date: 30-11-2007 [13] Wikipedia. June 13. last visit date: 30-11-2007 [14] Dr Emma Hart.uk/module. last visit date: 30-11-2007 [9] Michael Chung.J.doc.ac.edu.napier. [5] Mark A.ca/~mburo/ps/mcplan.generation5.org/wiki/Fuzzy_logic.au/~uqdjohns/publications/AI/AJIIPS_AI. Lecture Notes.cs. Charles River Media [8] T. last visit date: 30-11-2007 [16] Stuart James Kelly. and Jonathan Schaeffer. Charles River Media [7] Steve Rabin (edited by). http://www. AI Game Programming Wisdom. Jansen. http://www. Artificial_neural_network. http://www. 2003. Player Adaptive Cooperative Arti_cial Intelligence for RTS Games. 2000.

ca/users/reingold/courses/ai/nn. http://www. last visit date: 30-112007 [18] Artificial Intelligence in Games .com/KB/architecture/aigame. last visit date: 30-11-2007 . 1999.[17] Artificial Neural Networks.utoronto.aspx. http://www.psych. 17 Jul 2006.codeproject.html.