This action might not be possible to undo. Are you sure you want to continue?
1. What is Artificial Intelligence?
The basic objective of AI is to represent humans' thought processes in computers. These machines are supposed to exhibit behavior that, if performed by a human being, would be considered intelligent. An alternate definition, not covered in the text is by Astro Teller: "Artificial Intelligence (AI) is the science of how to get machines to do the things they do in the movies."
2. Major advantages and disadvantages of artificial intelligence over natural intelligence
• AI is Permanent • Can be easily duplicated • Can be less expensive • Can be documented
• Artificial intelligence is not creative • It is limited in the use of sensory devices • It cannot make use of a very wide context of experiences • It does not use common sense
3. Motivation for developing intelligent systems • •
Cost savings achieved by the reduction of employees Consistency in service provided to the end-users
4. Explain the role of the intelligent systems and their potential benefits
Intelligent systems are used to support decision-making and problem-solving applications. Their benefits include:
• • • •
Enhanced problem-solving Improved decision quality Ability to solve complex problems Consistent decisions.
5. What are the major difficulties in developing these systems?
The major difficulty in developing these systems is extracting the expertise needed to develop the knowledge base. It is difficult to extract an expert’s knowledge and codify it into a format that can be used in an automated application.
6. Major AI technologies: • • • • • • • • • • •
Expert systems Natural language processing Robotics Speech understanding Speech (voice) recognition Computer vision and scene recognition Intelligent computer-aided instruction Neural computing Intelligent agents Automatic programming Translation of languages
French. It learns your needs to serve you better.An expert system An expert system is a computer program that attempts to imitate human experts by the system's capability to render advice. E. Inference is the reasoning process of AI. They use inference methods to a specific body of knowledge called the domain. • • • • Knowledge base--the software that represents the knowledge/ expertise Working base—the data which is specific to a problem being solved Inference engine--the reasoning mechanism. 7. Major components of an ES. Speech understanding on the other hand is the computer's ability to understand a spoken language. The little paperclip guy that shows up in Microsoft Word is an example of an intelligent agent. User interface--the hardware and software exchange of ideas between people and the computer. For example. the computer understands the meaning of sentences and paragraphs through syntax and semantics. like any other agent working for you. It takes place in the brain of an AI process. Natural language processing Natural language processing is a program that permits (to a certain degree) a human-computer dialogue in a conversational. Bank Teller Machine. . day-to-day language (a natural language like English. Types of knowledge that comprise expertise • • • • • • Theories about the problem domain Rules and procedures regarding the general problem area Rules (heuristics) of what to do in a given problem situation Global strategies for solving these types of problems Meta-knowledge (knowledge about knowledge) Facts about the problem area 8. or Dutch). the computer recognizes and understands one (or a few) word commands. That is.g. to teach and execute intelligent tasks. Speech recognition and understanding Speech or voice recognition is a data input method. Intelligent agent An intelligent agent is a program that runs in the background and learns your patterns.
13. 14. Hybrid systems. Some knowledge engineers do the computer programming as well. Limitations of ES • • • • • • • • • • • Knowledge is not always readily available. Real-time systems. Time pressures. Knowledge is represented as a series of frames (an object-oriented approach). Requirements of ES: • • • Level of knowledge must be sufficiently high. Systems designed to produce a just-in-time response. that can be used by the expert system → User--the individual (non-expert) who uses the system for consultation. There are frequently multiple correct assessments. Inference can be performed using semantics networks. Frame-based systems. knowledge acquisition is a problem. Users have cognitive limits (limited knowledge on usage). It can be difficult to extract expertise from humans. 11. and logic statements. Help from knowledge engineers is difficult to obtain and costly. Potential for lack of trust on the part of the end-users. Role of a knowledge engineer? Knowledge engineering is the art of designing and building Expert Systems. How expert systems perform inference? The brain of an expert system is the inference engine that provides a methodology for reasoning about information in the knowledge base. Knowledge is represented by a series of rules. 15. Model-based systems. Most experts do not have an independent means to validate results. • • Ready-made systems. Major duties are to acquire and represent the knowledge. Utilize prepackaged software. . Structured around a model that simulates the structure and function of the system under study. Expertise must be available from at least one expert. 10. and an inference engine. The problem to be solved must by fuzzy. A shell is a piece of software which contains the user interface. Expert system shells Many expert systems are built with products called expert system shells. production rules. The knowledge and system engineers use these shells in making expert systems. Genetic categories of ES applications are: • • • • Rule-based ES. 12.9. Roles of individuals who interact with the system: → Domain expert--the individual who is considered an expert. a format for declarative knowledge in the knowledge base. Knowledge transfer is subject to biases. ES works well only within a narrow domain of knowledge. → Knowledge engineer--the individual who encodes the expert’s knowledge in a declarative form. Involve several approaches such as fuzzy logic and neural networks. Vocabulary is often limited and difficult to understand.
The user interface must be friendly to novice users. It provides more information. The problem to be solved must be difficult and important enough to justify the development of a system. 16. Information is more accurate (previously. which increases safety. improved quality of decision making It is faster and easier to set up and reschedule. • A wealth of historical data is available for planners. Maintenance/ Scheduling 4. 17. Design/ Configuration 5. General Problem Categories for ES/ Tasks done by ES • • • • • Interpretation – Forming high level conclusions from collections of raw date Prediction – Help to predict situations (e. Process Monitoring/ Controlling . the graphics are superb. major application categories of ES are. magnetic displays used to fall apart). Tsunami situation) Diagnosis – Determining reasons for malfunctions (failures) based on observable symptoms Designing – Finding a arrangement of system components that meets performance Planning – Planning a sequence of actions that will achieve a set of goals to given certain starting and runtime constraints • • • Monitoring – Comparing a system’s behavior to its expected behavior Instruction – Assisting by giving instructions in the education process in technical domains Control – Governing the behavior of a complex environment Those above areas can be categorized into six major areas. thus. Major benefits of the ES compared to the manual systems • • • • • • • • Cost Saving Accumulation of high quality knowledge into the shell. The shell must be of high quality and naturally store and manipulate the knowledge.• • • • • • • • The problem must be narrow in scope. 1. Knowledgeable developers with good people skills are needed. Management support is needed.g. Selection/ Classification 6. Thus. Preservation of scarce expertise It includes a built-in reminder system. Decision Management 2. Explanations of decisions recommended by the system are available (so training of new employees is faster). The impact should be favorable. Diagnostic/ Troubleshooting 3. The impact of the ES must be considered.
Expert Systems vs.. manufacturing Financial decision making – Insurance. Human Experts Human Experts Perishable Unpredictable Slow reproduction Expensive Slow processing Creative Adaptive Broad focus Common sense Expert System Permanent Consistent Quick replication Affordable Fast processing Lacks inspiration Needs instruction Narrow focus Machine knowledge .. Primary function is to deliver knowledge relevant to the user’s problem. Application and Examples for ES • • Diagnosis and troubleshooting of devices and systems – Medical diagnosis Planning scheduling. the manufacturing process planning and job scheduling • • • Configuration of manufactured objects from subassemblies – Modular home building. a tax advisor on tax strategy. Why go for ES • Helping in saving human lives (e.g.g. human experts are not always available where it is needed (e. Air craft engine monitoring systems) • • • • • For saving cost and time Since. Predicting trends. remote mining and drilling sites) The problems may be solved using symbolic reasoning Does not need sophistication and flexibility of humans Does not need human dexterity (use of hands) and perceptual skills 19. Expert Systems vs. Solution by.18. Loans to business and individuals. tactics and individual tax policy. an advisor on grammatical usage in a text.. Representation Execution Development of the system Conventional Information & control integrated Algorithm Numeric Generally sequential Considering how a computer would perform a task Expert Knowledge separate from control Rules & inference Symbolic Opportunistic rules Considering how a human expert would perform a task 21.. • Process monitoring and control – Do analysis of real-time data from physical devises. Conventional Programs Characteristic Control by. Medical expert system. failure corrections • Design and manufacturing – Assist in designing physical devices and processes 20. Two mostly known systems are.Airline scheduling of flights. foreign exchange trading Knowledge Publishing – Relatively new. Tsunami warning system. personnel and gates.
This action might not be possible to undo. Are you sure you want to continue?
We've moved you to where you read on your other device.
Get the full title to continue listening from where you left off, or restart the preview.