CSC 483:ARTIFICIAL

INTELLIEGENCE I
LECTURE 2023/2024
G O D F R E Y O KO Y E U N I V E R S I T Y, E N U G U
About me …

Ø Live in Kaiserslautern, Germany

Ø IT Product and Project Manager at SAP SE
Ø M.Sc. Computer Science at TUK
v major in Software Engineering
v minor in Intelligent Systems/AI
Ø B. Sc. Computer Science at GOU
v GOU Alumni; graduated 2017
v Overall Best Graduating Student 2017
Ø Email: catherinemaryugoji@gmail.com
Ø My LinkedIn
Ø Whatsapp: +4915211089216
About you…

On an index card or a piece of paper, write out the following about you;
q Name:
q Nickname:
q Background:
q Career/Academic Goals with fields of interest:
q Fun fact about you:
q Experience with GOU:
q Experience with online classes and exams so far:
Table of Content
In this course, we learn about;
1. Introduction to AI
a. Intelligence
b. Characteristics of AI
c. History of AI
2. Application of AI
a. Dominant fields of application of AI.
b. Research areas of AI
c. Real life applications of research areas of AI
d. Applications of AI and AI application etc.
3. Agents and Environments
4. Natural Language Processing (NLP)
5. Expert System; Knowledge Representation
6. Conclusion and future of AI
Course/ Coordination

Ø Classes will be on the Go-Uni virtual platform.

Ø You must be in attendance and on time, as attendance accounts for 5% of your grade.
Ø Attendance would be taken 5 mins after the class begins, if you join the class afterwards, you
loose part of the attendance points
Ø Failure to attend a class without prior or proper notification attracts a minus.
Ø Group exercise and presentation would account for 10 % of your grade (30th – 31st October)
Ø Mid-Course test = 15% of total grade (1st November)
Ø Course Revision and career discussion: 14th November (come prepared with your questions)
Ø Exam = 70% of total grade (15th of November)
Ø Always use my email or WhatsApp information for contact purposes and endeavor to join the
group chat as this would be my means of passing across any information, I deem necessary.
Introduction to Artificial
Intelligence (AI)
What is Intelligence?

q Intelligence:

§ According to Websters dictionary; “the capacity to learn and solve problems”

§ In particular,

o the ability to solve novel problems

o the ability to act rationally

o the ability to act like humans

What’s involved in Intelligence?

q Ability to interact with the real world

§ to perceive, understand, and act
§ e.g., speech recognition and understanding and synthesis
§ e.g., image understanding
§ e.g., ability to take actions, have an effect

q Reasoning and Planning

§ o modeling the external world, given input
§ o solving new problems, planning, and making decisions
§ o ability to deal with unexpected problems, uncertainties

q Learning and Adaptation

§ we are continuously learning and adapting
§ our internal models are always being “updated”
o e.g., a baby learning to categorize and recognize animals
Some Definitions of AI (I)

The exciting new effort to make

computers think …
machines with minds, in the full
and literal sense.
Haugeland, 1985

(exciting but not quite useful)

Some Definitions of AI (II)

A field of study that seeks to explain and emulate

intelligent behavior in terms of computational
processes.
Schalkoff, 1990

(Applied psychology & philosophy?)

Some Definitions of AI (III)

The study of how to make computers do

things at which, at the moment, people are
better.
Rich & Knight, 1991

(very close).
What is Artificial Intelligence (AI)?

q We can see AI as a way to enable people to accomplish more by collaborating with smart
software.
q Think of it as putting a more human face on technology;
§ Technology that can learn from the vast amounts of data that are available in the modern
world and technology that can understand our kind of language and respond in kind.
§ Technology that can see and interpret the world the way that we do.
q AI can revolutionize the way that computers and humans work together to create a better,
safer world.
q In the rest of this course, we will be exploring some of these technologies and how this kind of
technology works.
Real-World AI - Workplace Safety

https://www.youtube.com/watch?time_continue=29&v=pL-c00M2CnI&ab_channel=Microsoft
 What is Artificial Intelligence(AI)?

q According to the father of Artificial Intelligence, John McCarthy;

§ it is “The science and engineering of making intelligent machines,
especially intelligent computer programs”
§ It is related to the similar task of using computers to understand human
intelligence, but AI does not have to confine itself to methods that are
biologically observable.

q Artificial Intelligence is a way of making a computer, a computer-controlled

robot, or a software think intelligently, in the similar manner the intelligent
humans think.

(Formal definition)
AI is accomplished by

q … studying how human brain thinks, and how humans learn,

decide, and work while trying to solve a problem, and then using

the outcomes of this study as a basis of developing intelligent

software and systems.

Characteristics of Artificial Intelligence

1. Systems that act like humans

2. Systems that think like humans

3. Systems that think rationally

4. Systems that act rationally

1. Systems that act like humans

q "The automation of activities that we associate with human thinking, activities

such as decision-making, problem solving, learning...“
(Bellman, 1978)
q The Turing Test: Computing machinery and intelligence [Turing, 1950]
§ "Can machines think?" ⇒ "Can machines behave intelligently?"
§ Operational test for intelligent behavior = Imitation Game
q Problem: Turing test is not reproducible and not constructive.
2. Systems that think like humans

q "The art of creating machines that perform functions that require intelligence
when performed by people“
(Kurzweil, 1990)
q Cognitive Science
§ 1960s Cognitive Revolution: information processing psychology replaced
prevailing orthodoxy of behaviorism
§ Requires scientific theories of brain's internal activities
3. Systems that think rationally

q "The study of mental faculties through the use of computational models“

(Charniak and McDermott, 1985)
q Laws of Thought
§ Aristotle: what are correct arguments / thought processes?
§ Several Greek schools developed various forms of logic.
§ Direct line via mathematics and philosophy to modern AI
4. Systems that act rationally

q "The branch of computer science that is concerned with the automation of intelligent
behavior“
(Luger and Stubblefield, 1993)
q Doing the right thing
§ Rational behavior: doing the right thing
§ The right thing: which is expected to maximize goal achievement given the available
information
§ Doesn't necessarily involve thinking, but thinking should be in the service of
rational action.
What Contributes to AI?

q Artificial intelligence is a science and technology

based on various disciplines
q A major thrust of AI is in the development of
computer functions associated with human
intelligence, such as reasoning, learning, and
problem solving.
Programming Without and With AI
The programming without and with AI is different in following ways:
Programming Without AI
A computer program without AI can answer
the specific questions it is meant to solve.
Modification in the program leads to change
in its structure.
Modification is not quick and easy. It may
lead to affecting the program adversely.
Programming With AI
A computer program with AI can answer the
generic questions it is meant to solve.
AI programs can absorb new modifications
by putting highly independent pieces of
information together. Hence you can modify
even a minute piece of information of
program without affecting its structure.
Quick and Easy program modification.
Disciplines important to AI.
1. Philosophy Logic, methods of reasoning, mind as
physical system, foundations of learning, language,
rationality.
2. Mathematics/ algorithms: Formal representation and
proof, computation, (un)decidability, probability.
3. Neuroscience: neurons as information processing
units.
4. Psychology/Cognitive Science: how do people behave,
perceive, process information, represent knowledge.
5. Computer Science & Engineering: building fast
computers with intelligent software.
6. Sociology/Linguistics: knowledge representation,
grammar.
7. Biology: Modelling of Artificial Neural Networks
(ANN) like a brain network.
Difference between Human and Machine Intelligence

q Humans perceive by patterns whereas the machines perceive by set of

rules and data.
q Humans store and recall information by patterns, machines do it by
searching algorithms. For example, the number 40404040 is easy to
remember, store and recall as its pattern is simple.
q Humans can figure out the complete object even if some part of it is
missing or distorted; whereas the machines cannot correctly.
History of AI
Here is the history of AI during 20th century:
Year Milestone/Innovation

1943 § Foundations for neural networks laid

§ McCulloch & Pitts: Boolean circuit model of brain
1950 § Alan Turing introduced Turing Test for evaluation of intelligence and published Computing
Machinery and Intelligence
1956 § John McCarthy coined the term Artificial Intelligence.
§ Dartmouth meeting: Artificial Intelligence adopted
§ Demonstration of the first running AI program at Carnegie Mellon University.
1958 § John McCarthy invents LISP programming language for AI.

1964 § Danny Bobrow's dissertation at MIT showed that computers can understand natural language well
enough to solve algebra word problems correctly.
1965 § Joseph Weizenbaum at MIT built ELIZA, an interactive problem that carries on a dialogue in
English.
1969 § Scientists at Stanford Research Institute Developed Shakey, a robot, equipped with locomotion,
perception, and problem solving.
1973 § The Assembly Robotics group at Edinburgh University built Freddy, the Famous
Scottish Robot, capable of using vision to locate and assemble models.
1979 § The first computer-controlled autonomous vehicle, Stanford Cart, was built.

1986 § Rise of machine learning

1990 § Major advances in all areas of AI

• Significant demonstrations in machine learning algorithms and applications
• Neural networks
• Data mining, Web Crawler
• Natural language understanding and translation
• Vision, Virtual Reality
• Games etc.
1997 § The Deep Blue Chess Program beats the then world chess champion, Garry Kasparov.

2000 § Interactive robot pets become commercially available.

§ MIT displays Kismet, a robot with a face that expresses emotions.
§ The robot Nomad explores remote regions of Antarctica and locates meteorites
Applications of Artificial
Intelligence (AI)
Dominant Fields of Applications of AI
AI has been dominant in various fields such as:

1. Gaming: AI plays crucial role in strategic games such as chess, poker, tic-tac-toe, etc., where machine
can think of large number of possible positions based on heuristic knowledge.
2. Natural Language Processing: It is possible to interact with the computer that understands
natural language spoken by humans.
3. Expert Systems: There are some applications which integrate machine, software, and special
information to impart reasoning and advising. They provide explanation and advice to the users.
4. Vision Systems: These systems understand, interpret, and comprehend visual input on the
computer.
For example,
§ A spying airplane takes photographs which are used to figure out spatial information or map of
the areas .
§ Doctors use clinical expert system to diagnose the patient.
 § Police use computer software that can recognize the face of criminal with the stored
portrait made by forensic artist.
5. Speech Recognition: Some intelligent systems are capable of hearing and comprehending
the language in terms of sentences and their meanings while a human talks to it. It can handle
different accents, slang words, noise in the background, change in human’s noise due to cold, etc.
6. Handwriting Recognition: The handwriting recognition software reads the text written on
paper by a pen or on screen by a stylus. It can recognize the shapes of the letters and convert it
into editable text.
7. Intelligent Robots: Robots are able to perform the tasks given by a human. They have
sensors to detect physical data from the real world such as light, heat, temperature, movement,
sound, bump, and pressure. They have efficient processors, multiple sensors and huge memory,
to exhibit intelligence. In addition, they are capable of learning from their mistakes and they can
adapt to the new environment.
 Research Areas of AI

These are the large array of applications where AI is serving common people in their day-to-day lives
S/N Research Area Real Life Application

1 Expert Systems
Examples: Flight-tracking systems, Clinical systems

2 Natural Language Processing

Examples: Google Now feature, speech recognition,
Automatic voice output
3 Neural Networks
Examples: Machine learning and deep learning for
Pattern recognition systems such as face recognition,
character recognition, handwriting recognition.

4 Robotics
Examples: Industrial robots for moving, spraying,
painting, precision checking, drilling, cleaning, coating,
carving etc.

5 Fuzzy Logic
Examples: Consumer electronics, automobiles, etc.
Intelligent Systems in Your Everyday Life
q Post Office
§ automatic address recognition and sorting of mail
q Banks
§ automatic check readers, signature verification systems
§ automated loan application classification
q Telephone Companies
§ automatic voice recognition for directory inquiries
q Credit Card Companies
§ automated fraud detection
q Computer Companies
§ automated diagnosis for help-desk applications
q Netflix:
§ movie recommendation
q Google:
§ Search Technology
Let’s look at some examples of AI Applications
AI Applications 1: Consumer Marketing
q Have you ever used any kind of credit/ATM/store card while shopping?
§ if so, you have very likely been “input” to an AI algorithm
q All of this information is recorded digitally
q Companies like Nielsen gather this information weekly and search for patterns
§ general changes in consumer behavior
§ tracking responses to new products
§ identifying customer segments: targeted marketing, e.g., they find out that consumers with sports cars who
buy textbooks respond well to offers of new credit cards.
§ Currently a very hot area in marketing
q How do they do this?
§ Algorithms (“data mining”) search data for patterns
§ based on mathematical theories of learning
§ completely impractical to do manually
AI Applications 2: Identification Technologies

q ID cards
§ e.g., ATM cards
§ can be a nuisance and security risk:
o cards can be lost, stolen, passwords forgotten, etc
q Biometric Identification
§ walk up to a locked door
o camera
o fingerprint device
o microphone
o iris scan
§ computer uses your biometric signature for identification
o face, eyes, fingerprints, voice pattern, iris pattern
AI-Applications 3: Machine Translation

q Language problems in international business

§ e.g., at a meeting of Japanese, Korean, Vietnamese and Swedish investors, no
common language
§ or: you are shipping your software manuals to 127 countries
§ solution; hire translators to translate
§ would be much cheaper if a machine could do this!
q How hard is automated translation e.g. Using Google Translate App
§ very difficult!
§ e.g., English to Russian
o “The spirit is willing, but the flesh is weak” (English)
o “the vodka is good, but the meat is rotten” (Russian)
§ not only must the words be translated, but their meaning also!
AI-Applications: Exercise

q To be written in a group and this exercise would be graded and presented in the class
q The several sectors where artificial intelligence (AI) technologies are seeing rapid uptake:

1. AI in Transport with autonomous vehicles 11. AI in Human resources and Education

2. AI in Agriculture 12. AI in Hazardous environments
3. AI in Finance/Banking 13. AI in Space exploration.
4. AI in Marketing and advertising 14. AI in Entertainment
5. AI in Science 15. AI in Human Augmentation
6. AI in Healthcare 16. AI in Retail and E-commerce
7. AI in Criminal justice 17. AI in Gaming
8. AI in Security/Cybersecurity 18. AI in Fashion
9. AI in the Public sector 19. AI in Social Media
10. AI in and using augmented and virtual reality. 20. AI in Military & Defense
Agents and
Environments
 Agents and environments
q An agent is anything that can perceive its
environment through sensors and acts upon
that environment through effectors.
q An agent could take various forms;
1. A human agent has sensory organs
such as eyes, ears, nose, tongue and
skin parallel to the sensors, and other
organs such as hands, legs, mouth, for effectors.
2. A robotic agent replaces cameras and infrared range
finders for the sensors, and various motors and actuators for
effectors.
3. A software agent has encoded bit strings as its programs and
actions
Types of agents

q Agent’s structure can be viewed as:

§ Agent = Architecture + Agent Program
§ Architecture = the machinery that an agent
executes on.
§ Agent Program = an implementation of an agent
function.

q Four basic agent types in order of increasing generality:

1. Simple reflex agent
2. Model-Based Reflex Agents
3. Goal-based agent
4. Utility-based agent
1. Simple Reflex Agents

q They choose actions only based on

the current percept.
q They are rational only if a correct
decision is made only on the basis
of current precept.
q Their environment is completely
observable.
q Condition-Action Rule: It is a
rule that maps a state (condition)
to an action
2. Model-Based Reflex Agents

q They use a model of the world to choose their

actions. They maintain an internal state.
q Model: knowledge about “how the things
happen in the world”.
q Internal State: It is a representation of
unobserved aspects of current state
depending on percept history.
q Updating state requires the
information about
§ How the world evolves.
§ How the agent’s actions affect the world.
q Advanced Condition-Action Rule
 3. Goal-Based Agents

q They choose their actions in

order to achieve goals.
q Goal-based approach is more
flexible than reflex agent since
the knowledge supporting a
decision is explicitly modeled,
thereby allowing for
modifications.
q Goal: It is the description of
desirable situations.
4. Utility-Based Agents

q They choose actions based on a

preference (utility) for each state.
q Goals are inadequate when:
§ There are conflicting goals
only some of which can be
achieved.
§ Goals have some uncertainty
of being achieved and one
needs to weigh likelihood of
success against the
importance of a goal.
Properties of Environment
q The environment has multifold properties:
1. Discrete / Continuous: If there are a limited number of distinct, clearly defined, states of the
environment, the environment is discrete (For example, chess); otherwise it is continuous (For
example, driving).
2. Observable / Partially Observable: If it is possible to determine the complete state of the
environment at each time point from the percepts it is observable; otherwise it is only partially
observable.
3. Static / Dynamic: If the environment does not change while an agent is acting, then it is static;
otherwise it is dynamic.
4. Single agent / Multiple agents: The environment may contain other agents which may be of the
same or different kind as that of the agent.
5. Accessible vs. inaccessible: If the agent’s sensory apparatus can have access to the complete
state of the environment, then the environment is accessible to that agent.
6. Deterministic vs. Non-deterministic: If the next state of the environment is completely
determined by the current state and the actions of the agent, then the environment is deterministic;
otherwise it is non-deterministic.
7. Episodic vs. Non-episodic: In an episodic environment, each episode consists of the agent
perceiving and then acting. The quality of its action depends just on the episode itself. Subsequent
episodes do not depend on the actions in the previous episodes. Episodic environments are much
simpler because the agent does not need to think ahead.
Natural Language Processing
Understanding Language
q The main aspect of intelligence separating humans from other animals is our use of
language.
q We are unique in our ability to articulate complex ideas, explanations, and series of events
as well as understand them when told to us by others.
q Thousands of other abilities also contribute to our intelligence, but the use of language as
a means of communicating complicated ideas trumps them all.
q For intelligent systems to partner with us in the workplace or elsewhere, they must
genuinely understand us and then communicate what they are doing back to us in a way
that we can comprehend.
q Our willingness to accept Siri, Cortana etc and other personal assistants as intelligent is
based almost entirely on their ability to interact with us using spoken language. The fact
that their ability to do things for us is somewhat limited is far less important to us (or
even noticeable to us) than the fact that they use language.
Processing Language

q The goal of natural language understanding (NLU) systems is to

figure out the meaning of language inputs: the words, sentences, stories,
and so on.
q Systems aimed at this problem use a combination of three different
kinds of information:
§ Pragmatics: Contextual information such as lists or descriptions.
§ Semantics: The meaning of words and how those meanings can
be combined.
§ Syntax: The structural relationships among types of language
elements such as nouns, verbs, adjectives, prepositions, and
phrases.
Natural Language Processing (NLP)

q Natural Language Processing (NLP) refers to AI method of

communicating with an intelligent systems using a natural language such
as English.
q Processing of Natural Language is required when you want an intelligent
system like robot to perform as per your instructions, when you want to
hear decision from a dialogue based clinical expert system, etc.
q The field of NLP involves making computers to perform useful tasks with
the natural languages' humans use.
q The input and output of an NLP system can be:
§ Speech
§ Written Text
Components of NLP
There are two components of NLP as given:
1. Natural Language Understanding (NLU): Understanding involves the following tasks:
q Mapping the given input in natural language into useful representations.
q Analyzing different aspects of the language.
2. Natural Language Generation (NLG): It is the process of producing meaningful phrases
and sentences in the form of natural language from some internal representation. It involves:
q Text planning: It includes retrieving the relevant content from knowledge base.
q Sentence planning: It includes choosing required words, forming meaningful phrases,
setting tone of the sentence.
q Text Realization: It is mapping sentence plan into sentence structure.

Ø The NLU is harder than NLG.

Difficulties in NLU
q NL (Natural Language) has an extremely rich form and structure.
q It is very ambiguous. There can be different levels of ambiguity:
§ Lexical ambiguity: It is at very primitive level such as word-level.
o For example, treating the word “board” as noun or verb?
§ Syntax Level ambiguity: A sentence can be parsed in different
ways.
o For example, “He lifted the beetle with red cap.” – Did he use
cap to lift the beetle or he lifted a beetle that had red cap?
§ Referential ambiguity: Referring to something using pronouns.
o For example, Rima went to Gauri. She said, “I am tired.” -
Exactly who is tired?
§ One input can mean different meanings.
§ Many inputs can mean the same thing.
Steps in Natural Language Processing (NLP)
There are generally five steps:
1. Lexical Analysis:
§ It involves identifying and analyzing the structure of words.
§ Lexicon of a language means the collection of words and phrases in a language.
§ Lexical analysis is dividing the whole chunk of text into paragraphs, sentences, and words.
2. Syntactic Analysis (Parsing):
§ It involves analysis of words in the sentence for grammar and arranging words in a manner that
shows the relationship among the words.
§ The sentence such as “The school goes to boy” is rejected by English syntactic analyzer.
3. Semantic Analysis:
§ It draws the exact meaning or the dictionary meaning from the text.
§ The text is checked for meaningfulness.
§ The semantic analyzer disregards sentence such as “hot ice-cream”.
4. Discourse Integration:
§ The meaning of any sentence depends upon the meaning of the sentence just before it.
§ In addition, it also brings about the meaning of immediately succeeding sentence.
5. Pragmatic Analysis:
§ During this, what was said is re-interpreted on what it actually meant.
§ It involves deriving those aspects of language which require real world knowledge.
Expert System(ES); Knowledge and
Reasoning
What are Expert Systems?
q The expert systems are the computer applications
developed to solve complex problems in a particular
domain, at the level of extra-ordinary human intelligence
and expertise.

q Characteristics of Expert Systems

§ High performance
§ Understandable
§ Reliable
§ Highly responsive
Capabilities of Expert Systems
The expert systems are capable of: They are incapable of:
q Advising q Substituting human decision makers
q Instructing and assisting human in decision q Possessing human capabilities
making q Producing accurate output for inadequate knowledge
q Demonstrating base
q Deriving a solution q Refining their own knowledge
q Diagnosing
q Explaining
q Interpreting input
q Predicting results
q Justifying the conclusion
q Suggesting alternative options to a problem
Components of Expert Systems

The components of ES include:

1. Knowledge Base
2. Inference Engine
3. User Interface
Knowledge Base

q It contains domain-specific and high-quality knowledge.

q Intelligent agents need knowledge about the world in
order to reach good decisions.
q Humans use huge amounts of common-sense knowledge
to solve even tiny tasks.
q Knowledge is required to exhibit intelligence. The success
of any ES majorly depends upon the collection of highly
accurate and precise knowledge.
q Knowledge is stored in the form of sentences in a
knowledge representation language that are stored in a
knowledge base.
What is Knowledge?

q Data is collection of facts.

q Information is organized as data and facts about the task domain.
q Data, information, and past experiences combined together are termed as
knowledge.

Components of Knowledge Base

q The knowledge base of an ES is a store of both, factual and

heuristic knowledge.
1. Factual Knowledge – It is the information widely accepted by
the Knowledge Engineers and scholars in the task domain.
2. Heuristic Knowledge – It is about practice, accurate
judgment, one’s ability of evaluation, and guessing.
Knowledge representation
q It is the method used to organize and formalize the knowledge in the knowledge base.
q It is in the form of IF-THEN-ELSE rules.

Knowledge Acquisition
q The success of any expert system majorly depends on the quality, completeness, and accuracy of the
information stored in the knowledge base.
q The knowledge base is formed by readings from various experts, scholars, and the Knowledge Engineers.
q The knowledge engineer is a person with the qualities of empathy, quick learning, and case analyzing skills.
§ He acquires information from subject expert by recording, interviewing, and observing him at work, etc.
§ He then categorizes and organizes the information in a meaningful way to be used by interference
machine.
§ The knowledge engineer also monitors the development of the ES.
Conclusion
Conclusion & The Future of AI
q Since the invention of computers or machines, their capability to perform various tasks went on growing
exponentially.
q Humans have developed the power of computer systems in terms of their diverse working domains, their
increasing speed, and reducing size with respect to time.
q Given the pace of adoption and popularity of AI, it is headed towards a future where: e.g. Automated
transportation will become more common.
q There will be an increased prevalence of smart cities where vehicles, phones, and home appliances will be run by
AI.
q Human augmentation, where robots (as tech billionaire and Tesla head, Elon Musk puts it —) would “be able to
do everything better than us…”
q Robots will perform jobs that are potentially dangerous to humans, such as defusing bombs, lifting heavy
objects, working in high-risk factories, or handling hazardous substances, etc.
q As the AI revolution continues to gather steam, we’ll witness disruptive innovations that will test the boundaries
of our imagination.
Video Analysis

qhttps://www.youtube.com/watch?v=0egaiR8zlw4&ab_channel=SASSoftw
are
qhttps://www.youtube.com/watch?v=cPZvDg6Tw5Q&ab_channel=GreatLe
arning
qhttps://www.youtube.com/watch?v=nOnsbd7rdhc&ab_channel=OriginsE
xplained