3/9/2022

MENE 5223 Artificial Intelligence

Wong Yan Chiew

BSc (UTM), Meng. (UTM), Dr. (UOE, United Kingdom)
ycwong@utem.edu.my

Updated version: Feb 2022

Teaching Plan

1
 3/9/2022

Chapter 1: Introduction to Artificial

Intelligence
Outline:

1.1 Introduction to Artificial Intelligence

▪ What is intelligence?
▪ Artificial intelligence and its approaches
▪ Components of Intelligence
▪ AI objectives
▪ The foundations of AI
▪ History of AI

1.2 Intelligent Agents

▪ General Properties of AI Systems
▪ The nature of agents
▪ The structure of Intelligent agent

Chapter 1: Introduction to Artificial

Intelligence
Outline:

1.3 AI Techniques
▪ Describe & match
▪ Constrain satisfaction
▪ Rule based systems
▪ Search algorithms
▪ Informed (Heuristic) search strategies
▪ Stochastic methods
▪ Regression techniques

1.4 AI applications
▪ AI Tree
▪ The state of the art
▪ AI issues

2
 3/9/2022

What is Intelligence?

The ability of a system to calculate, reason, perceive

relationships and analogies, learn from experience,
store and retrieve information from memory, solve
problems, comprehend complex ideas, use natural
language fluently, classify, generalize, and adapt
new situations.

Types of Intelligence

As described by Howard Gardner, an American developmental psychologist, the

Intelligence comes in multifold −

Intelligence Description Example

The ability to speak, recognize, and use

mechanisms of phonology (speech
Linguistic intelligence Narrators, Orators
sounds), syntax (grammar), and
semantics (meaning).

The ability to create, communicate with,

Musicians, Singers,
Musical intelligence and understand meanings made of
Composers
sound, understanding of pitch, rhythm.

The ability of use and understand

relationships in the absence of action or Mathematicians,
Logical-mathematical intelligence
objects. Understanding complex and Scientists
abstract ideas.

3
 3/9/2022

Types of Intelligence

Intelligence Description Example

The ability to perceive visual or spatial

As described by Howard Gardner, an American
information, developmental
change it, and re-create psychologist, the
Intelligence comes in multifold − visual images without reference to the Map readers,
Spatial intelligence
Astronauts, Physicists
objects, construct 3D images, and to
move and rotate them.

The ability to use complete or part of

the body to solve problems or fashion
Bodily-Kinesthetic intelligence products, control over fine and coarse Players, Dancers
motor skills, and manipulate the
objects.

The ability to distinguish among one’s

Intra-personal intelligence own feelings, intentions, and Gautam Buddhha
motivations.

The ability to recognize and make

Mass Communicators,
Interpersonal intelligence distinctions among other people’s
Interviewers
feelings, beliefs, and intentions.

7
You can say a machine or a system is artificially intelligent when it is equipped with at least one and at most all intelligences in it.

Intelligence
(perceive, understand, predict and manipulate)

“the capacity to learn and solve problems”

(Websters dictionary)
in particular,

the ability to solve novel problems

the ability to act rationally
the ability to act like humans

4
 3/9/2022

Intelligence
Relate to tasks involving higher mental processes.
Examples:
creativity, solving problems, pattern recognition,
classification, learning, induction, deduction,
building analogies, optimization, language
processing, knowledge and many more.

Intelligence is the computational part of the ability

to achieve goals.

Artificial Intelligence

Not just to understand but also to build

intelligent entities or agents.

Relevant to any intellectual task (playing

chess, proving mathematical theorems,
writing poetry, driving, etc)

10

5
 3/9/2022

What is Artificial Intelligence?

According to the father of Artificial Intelligence, John McCarthy, it is “The science and
engineering of making intelligent machines, especially intelligent computer programs”.

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.

AI is accomplished by
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.
11

11

AI fall into two dimensions, four approaches:

Thought processes and reasoning
Thinking humanly Thinking rationally
“the exciting new effort to make “The study of mental faculties
Ideal performance measure, called rationality

computer think ….machines with minds, in through the use of computational

•
the full and literal sense.” (Haugeland, models” (Charniak and McDermott,
Fidelity to human performance

1985) 1985)
“[The automation of] activities that we “the study of computations that
associate with human thinking, activities make it possible to perceive,
such as decision-making, problem solving, reason, and act.” (Winston, 1992)
learning ...” (Bellman, 1978)
Acting humanly Acting rationally
“The art of creating machines that “computational intelligence is the
perform functions that require study of the design of intelligent
intelligence when performed by people” agents.” (Poole et al., 1998)
(Kurzweil, 1990)
“AI … is concerned with intelligent
“the study of how to make computers do behavior in artifacts.” (Nilsson,
things at which, at the moment, people 1998)
are better.” (Rich and Knight, 1991)
behavior
12

6
 3/9/2022

13

Thinking humanly: cognitive modeling

▪ An exciting new effort to make computers think; that it is, the machines with
minds, in the full and literal sense.
▪ Requires scientific theories of internal activities of the brain.

How to validate? Requires

1) Predicting and testing behavior of human subjects
(top-down)
or 2) Direct identification from neurological data (bottom-up)

Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now
distinct from AI.

▪ Focus is not just on behavior and I/O, but looks at reasoning process.
▪ Computational model as to how results were obtained.

14

14

7
 3/9/2022

Thinking humanly: cognitive modeling

Goal is not just to produce human-like behavior

but to produce a sequence of steps of the
reasoning process, similar to the steps followed by
a human in solving the same task.

Do we want to duplicate human imperfections?

15

15

Acting humanly: Turing Test

• Turing (1950) "Computing machinery and intelligence":
• "Can machines think?"  "Can machines behave intelligently?"
• Operational test for intelligent behavior: the Imitation Game
• Focus is on action, and not intelligent behaviour centered around
representation of the world.

• Predicted that by 2000, a machine might have a 30% chance of

fooling a lay person for 5 minutes

16

16

8
 3/9/2022

Acting humanly: Turing Test

▪ To pass a rigorously applied test, the computer would need
to possess the following capabilities:
✓ natural language processing to enable it to communicate
successfully in English
✓ Knowledge representation to store what it knows or hears;
✓ Automated reasoning to use the stored information to
answer questions and to draw new conclusions;
✓ Machine learning to adapt to new circumstances and to
detect and extrapolate patterns.

17

17

Acting humanly: Turing Test

▪ Direct physical interaction between the interrogator and the computer is deliberately avoided
▪ Physical simulation of a person is unnecessary for intelligence
▪ Total Turing Test – a video signal for the interrogator to test the subject’s perceptual abilities
and to pass physical objects “through the hatch”
▪ To pass the TTT, the computer will need:
✓computer vision to perceive objects, and
✓Robotics to manipulate objects and move about

* Question: is it important that an intelligent system act like a human?

18

18

9
 3/9/2022

The Turing test: Can a computer pass for a human?

What is consciousness? Can an artificial machine really think? For many, these have been vital
considerations for the future of artificial intelligence. But British computer scientist Alan Turing decided
to disregard all these questions in favor of a much simpler one: Can a computer talk like a human? Alex
Gendler describes the Turing test and details some of its surprising results.

19

What can people do that computers can’t do?

• A CAPTCHA is a program that protects websites against bots by generating and

grading tests that humans can pass but current computer programs cannot. For
example, humans can read distorted text as the one shown below, but current
computer programs can't:

• The term CAPTCHA (for Completely Automated Public Turing Test To Tell Computers
and Humans Apart) was coined in 2000 by Luis von Ahn, Manuel Blum, Nicholas
Hopper and John Langford of Carnegie Mellon University.

20

20

10
 3/9/2022

Chess

Name: Garry Kasparov

Title: World Chess
Champion

Humans are still better at making up excuses.

21

21

Chess

22

22

11
 3/9/2022

Many of the white-collar jobs will

move into the machines’ domain.”

Artificial Intelligence will show us

our true selves. It;Its not here to
replace us …it will remind us of
what makes us human
23

23

Chess

24

24

12
 3/9/2022

Perspective on Chess: Pro

“Saying Deep Blue doesn’t really think

about chess is like saying an airplane
doesn't really fly because it doesn't flap
its wings”
Drew McDermott

25

25

Perspective on Chess: Con

“Chess is the Drosophila of artificial
intelligence. However, computer chess has
developed much as genetics might have if the
geneticists had concentrated their efforts
starting in 1910 on breeding racing Drosophila.
We would have some science, but mainly we
would have very fast fruit flies.”
John McCarthy

Drosophila of AI – a reference to the fruit flies biologists used to

uncover the secrets of genetics and McCarthy believed his
successors in AI research had taken the analogy too far.

26

26

13
 3/9/2022

27

27

28

28

14
 3/9/2022

Thinking rationally: "laws of thought"

▪ The study of mental faculties through the use of computational models; that it is, the study of the
computations that make it possible to perceive, reason, and act.
▪ Focus is on inference mechanisms that are provably correct and guarantee an optimal solution.
▪ Govern the operation of the mind; initiated the field called logic
▪ Develop systems of representation to allow inferences to be like “Socrates is a man. All men are
mortal. Therefore Socrates is mortal.”

29

29

Thinking rationally: "laws of thought"

An inference is a process of drawing conclusions based on the evidence. On the basis of some
evidence or a “premise,” you infer a conclusion. For example:

30

30

15
 3/9/2022

Thinking rationally: "laws of thought"

There are also bad inferences, or inferences that may appear persuasive that on further inspection turn
out to be misleading. For example:

The strength of your argument depends entirely on two things: the accuracy of your evidence,
and the strength of your inferences. If you have solid evidence and you draw valid inferences,
your argument will be complete. 31

31

Thinking rationally: "laws of thought"

The validity of an inference depends on the form of the inference.

That is, the word "valid" does not refer to the truth of the premises or the conclusion, but rather to the
form of the inference.

An inference can be valid even if the parts are false, and can be invalid even if some parts are true. But
a valid form with true premises will always have a true conclusion.
For example, consider the form of the following symbological track:
1. All meat comes from animals.
2. All beef is meat.
3. Therefore, all beef comes from animals.
If the premises are true, then the conclusion is necessarily true, too.

Now we turn to an invalid form.

1. All A are B.
2. All C are B.
3. Therefore, all C are A.
To show that this form is invalid, we demonstrate how it can lead from true premises to a false
conclusion.
1. All apples are fruit. (True)
2. All bananas are fruit. (True)
3. Therefore, all bananas are apples. (False)

32

32

16
 3/9/2022

Types of Inferences
There are two basic types of inference:
a. Deduction (or “deductive inference”) is an inference based on logical certainty. It
usually starts from a general principle and then infers something about specific cases.

“Grapes are poisonous to all dogs”

This allows you to infer that grapes are poisonous for your dog, too. If the premise is true
then the conclusion has to be true. There’s no other possibility. Notice, however, that this
doesn’t really tell you anything new: once you say “grapes are poisonous to all dogs,” you
already know that grapes are poisonous for your specific dog. Deduction has the
advantage of certainty, but it doesn’t generate new knowledge.

b. Induction (or “inductive inference”) is an inference based on probability. It usually starts

from specific information and then infers the more general principle.

“For the last two years, Amanda has woken up at 8am every day”

This allows you to infer that Amanda will probably wake up at 8am tomorrow, too. You
would probably be right, and it’s a reasonable inference but it’s not certain! Tomorrow
could be the first day that Amanda decides to sleep in. Despite this uncertainty, however,
induction does offer the possibility of predicting future events and creating new knowledge.
33

33

Thinking rationally: "laws of thought"

▪ Goal is to formalize the reasoning process as a

system of logical rules and procedures for
inference.
▪ The issue is, not all problems can be solved
just by reasoning and inferences.
▪ Ignores role of consciousness, emotions, fear of
dying on intelligence.

34

34

17
 3/9/2022

Thinking rationally: "laws of thought"

Inference
Inference is the act or process of deriving a conclusion based
solely on what one already knows; it is deduction of new facts
from old ones; Logic captures inference.

35

35

36

36

18
 3/9/2022

Acting rationally: rational agent

• An agent is just something that acts.
• Computer agents: operate autonomously, perceive their
environment, persists over a prolonged time period, adapt to
change, create and pursue goals.
• Rational behavior: doing the right thing
• The right thing: that which is expected to maximize goal
achievement, given the available information and uncertainties
• Focus is on systems that act sufficiently if not optimally in all
situations.
• Goal is to develop systems that are rational and sufficient.

37

37

Intelligent Behavior
▪ Perceiving one’s environment,
▪ Acting in complex environments,
▪ Learning and understanding from experience,
▪ Reasoning to solve problems and discover hidden
knowledge,
▪ Knowledge applying successfully in new situations,
▪ Thinking abstractly, using analogies,
▪ Communicating with others, and more like
▪ Creativity, Ingenuity, Expressiveness, Curiosity.

38

19
 3/9/2022

What is Intelligence Composed of?

39

39

What is Intelligence Composed of?

Let us go through all the components briefly −

• Reasoning − It is the set of processes that enables us to provide basis
for judgement, making decisions, and prediction. There are broadly two
types −

Inductive Reasoning Deductive Reasoning

It conducts specific observations to makes broad It starts with a general statement and examines the
general statements. possibilities to reach a specific, logical conclusion.

Even if all of the premises are true in a statement, If something is true of a class of things in general, it
inductive reasoning allows for the conclusion to be is also true for all members of that class.
false.

Example − "All women of age above 60 years are

Example − "Nita is a teacher. Nita is studious.
grandmothers. Shalini is 65 years. Therefore, Shalini
Therefore, All teachers are studious."
is a grandmother."

40

40

20
 3/9/2022

What is Intelligence Composed of?

Learning − It is the activity of gaining knowledge or skill by studying, practising, being taught,
or experiencing something. Learning enhances the awareness of the subjects of the study.

The ability of learning is possessed by humans, some animals, and AI-enabled systems. Learning is
categorized as −

◦ Auditory Learning − It is learning by listening and hearing. For example, students

listening to recorded audio lectures.
◦ Episodic Learning − To learn by remembering sequences of events that one has
witnessed or experienced. This is linear and orderly.
◦ Motor Learning − It is learning by precise movement of muscles. For example, picking
objects, Writing, etc.
◦ Observational Learning − To learn by watching and imitating others. For example, child
tries to learn by mimicking her parent.
◦ Perceptual Learning − It is learning to recognize stimuli that one has seen before. For
example, identifying and classifying objects and situations.
◦ Relational Learning − It involves learning to differentiate among various stimuli on the
basis of relational properties, rather than absolute properties. For Example, Adding ‘little
less’ salt at the time of cooking potatoes that came up salty last time, when cooked with
adding say a tablespoon of salt.
◦ Spatial Learning − It is learning through visual stimuli such as images, colors, maps, etc.
For Example, A person can create roadmap in mind before actually following the road.
◦ Stimulus-Response Learning − It is learning to perform a particular behavior when a
certain stimulus is present. For example, a dog raises its ear on hearing doorbell.

41

41

What is Intelligence Composed of?

• Problem Solving − It is the process in which one perceives and tries to

arrive at a desired solution from a present situation by taking some path,
which is blocked by known or unknown hurdles.
Problem solving also includes decision making, which is the process of
selecting the best suitable alternative out of multiple alternatives to reach
the desired goal are available.

• Perception − It is the process of acquiring, interpreting, selecting, and

organizing sensory information.
Perception presumes sensing. In humans, perception is aided by sensory
organs. In the domain of AI, perception mechanism puts the data
acquired by the sensors together in a meaningful manner.

• Linguistic Intelligence − It is one’s ability to use, comprehend, speak,

and write the verbal and written language. It is important in interpersonal
communication.

42

42

21
 3/9/2022

Difference between Human and Machine Intelligence

• Humans perceive by patterns whereas the machines perceive

by set of rules and data.
• 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.
• Humans can figure out the complete object even if some part
of it is missing or distorted; whereas the machines cannot do
it correctly.

43

43

Intelligent Behavior
Jimmy Meets Sophia the Human-Like Robot

44

22
 3/9/2022

Understanding AI

▪ How knowledge is acquired, represented, and

stored;
▪ How intelligent behavior is generated and learned;
▪ How motives, emotions, and priorities are
developed and used;
▪ How sensory signals are transformed into symbols;
▪ How symbols are manipulated to perform
logic, to reason about past, and plan for future;
▪ How mechanisms of intelligence produce the
phenomena of illusion, belief, hope, fear, dreams,
kindness and love.”

45

Hard/Strong AI
▪ Generally, artificial intelligence research aims to create AI
that can replicate human intelligence completely.

▪ Strong AI refers to a machine that approaches or supersedes

human intelligence,
◊ If it can do typically human tasks,
◊ If it can apply a wide range of background knowledge and
◊ If it has some degree of self-consciousness.

▪ Strong AI aims to build machines whose overall intellectual

ability is indistinguishable from that of a human being.

46

23
 3/9/2022

Soft/Weak AI
▪ Weak AI refers to the use of software to study or
accomplish specific problem solving or reasoning
tasks that do not encompass the full range of
human cognitive abilities.
Example : a chess program such as Deep Blue.

▪ Weak AI does not achieve self-awareness; it

demonstrates wide range of human-level cognitive
abilities; it is merely an intelligent, a specific
problem-solver.

47

AI Advantages Over Natural Intelligence

• More permanent
• Ease of duplication and dissemination
• Less expensive
• Consistent and thorough
• Can be documented
• Can execute certain tasks much faster than a
human
• Can perform certain tasks better than many or
even most people
48

48

24
 3/9/2022

Natural Intelligence Advantages over AI

• Natural intelligence is creative

• People use sensory experience directly
• Can use a wide context of experience in different
situations

AI - Very Narrow Focus

49

49

Questions to be discussed

▪ Can Computers Talk?

▪ Can Computers Recognize Speech?
▪ Can Computers Understand speech?
▪ Can Computers Learn and Adapt ?
▪ Can Computers “see”?
▪ Can computers plan and make optimal
decisions?

50

50

25