Introduction to Artificial Intelligence

CoSc 4061
Prerequisites: Logic in computer science

Chapter One

1
Outline
 Basic Concepts of an Artificial Intelligence
 Introduction to Artificial Intelligence

 Application of AI and Areas of Study

 Future and Benefits of A.I.

 History of AI

 Foundations of AI

 Components of an AI System

2
 Introduction
Introduction
What is Artificial Intelligence (AI) ?
Artificial Intelligence is composed of two words Artificial and Intelligence.

Artificial defines "man-made," and intelligence defines

"thinking power", or “the ability to learn and solve problems”
hence Artificial Intelligence means "a man-made thinking power."
So, we can define Artificial Intelligence (AI) as the branch of
computer science by which we can create intelligent machines
which can behave like a human, think like humans, and able to
make decisions.
Introduction…
Why we are interested in AI?

To develop intelligent entities

AI is based on the premise/that: Human mind can be

explained in terms of computation, and Computers can
do the right thing given correct premises and reasoning
rules

4
Artificial intelligence can be viewed from a variety of perspectives.

I. From the perspective of intelligence:

 AI is making machines "intelligent" -- acting as we would expect
people to act.

II. From a business perspective

 AI is a set of very powerful tools, and a methodologies for using
those tools to solve business problems.

III. From a programming perspective:

 AI includes the study of symbolic programming, problem solving,
and search.
 Typically AI programs focus on symbols rather than numeric
processing.
5
 AI programming languages include
1) LISP, developed in the 1950s, is the early programming language
strongly associated with AI.

 LISP is a functional programming language with procedural extensions.

LISP (LISt Processor) was specifically designed for processing

heterogeneous lists -- typically a list of symbols.

2. The second language strongly associated with AI is PROLOG.

PROLOG was developed in the 1970s. PROLOG is based on first order
logic.

PROLOG is declarative in nature and has facilities for explicitly limiting the
search space.

6
 Definition of Artificial Intelligence?
 Artificial Intelligence (AI) is a branch of Science which deals

with helping machines find solutions to complex problems in a

more human-like fashion. Borrowing characteristics from human
intelligence, and applying them as algorithms in a computer
friendly way.
 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.

Examples of these tasks are visual perception, speech recognition,

decision-making, and translation between languages.
7
Cont…
Making computers that think?

The automation of activities we associate with human thinking,

like decision making, learning ... ?

The art of creating machines that perform functions that require

intelligence when performed by people ?

The study of mental faculties through the use of computational

models ?
Cont…
The study of computations that make it possible to perceive,
reason and act ?

a field of study that seeks to explain and emulate intelligent

behaviour in terms of computational processes

a branch of computer science that is concerned with the

automation of intelligent behaviour

anything in Computing Science that we don't yet know how

to do properly
….What is the definition of AI?

What do you think?

10
 …What is the definition of AI?

Systems that think like humans Systems that think rationally

Systems that act like humans Systems that act rationally

11
 …What is the definition of AI?

Systems that think like Systems that think rationally

humans
Systems that act like humans Systems that act rationally

Bellman, 1978
“[The automation of] activities that we associate with human thinking,
activities such as decision making, problem solving, learning”

12
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Charniak & McDermott, 1985

“The study of mental faculties through the use of computational
models”

13
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Dean et al., 1995

“The design and study of computer programs that behave intelligently.
These programs are constructed to perform as would a human or an
animal whose behavior we consider intelligent”

14
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Haugeland, 1985
“The exciting new effort to make computers think machines with
minds, in the full and literal sense”

15
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Kurzweil, 1990
“The art of creating machines that perform functions that require
intelligence when performed by people”

16
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Luger & Stubblefield, 1993

“The branch of computer science that is concerned with the automation
of intelligent behavior”

17
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Nilsson, 1998
“Many human mental activities such as writing computer programs,
doing mathematics, engaging in common sense reasoning,
understanding language, and even driving an automobile, are said to
demand intelligence. We might say that [these systems] exhibit
artificial intelligence”

18
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Rich & Knight, 1991

“The study of how to make computers do things at which, at the
moment, people are better”

19
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Schalkoff, 1990
“A field of study that seeks to explain and emulate intelligent behavior
in terms of computational processes”

20
 What is the definition of AI?
Systems that think like Systems that think rationally
humans
Systems that act like humans Systems that act rationally

Winston, 1992
“The study of the computations that make it possible to perceive,
reason, and act”

21
Areas of AI and Some Dependencies

Knowledge
Search Logic Representation

Machine
Planning
Learning

Expert
NLP Vision Robotics Systems
AI Advocators
• AI advocators publicly support/recommends on the
ultimate goal
– AI researchers are generally categorized as weak and
strong AI advocators
– Strong AI advocators
• In the future technologists will one day be able to build a
computer with all cognitive, memory, and emotional
capabilities of the human brain.
• They believe that computers will someday be more
intelligent than human beings
– Weak AI advocators
• If people need to make a computer that thinks, they should
replace the circuits with proteins
• They believe that we will achieve to build robust computer
systems that mostly provide decision support and decision
making

23
Weak A.I.
Machines with weak AI are made to respond to specific
situations, but can not think for themselves

Strong A.I.
A machine with strong A.I. is able to think and act just like a
human. It is able to learn from experiences.
Since there are no real life examples of strong A.I. yet, the
best representation would be how Hollywood portrays robots.
General AI goal
– Replicate human intelligent
– Solve knowledge intensive/Sever/ task
– Make an intelligent connection between
perception (insight, sense, become aware) and action
– Enhance human-computer interaction/
communication

25
General AI goal
• Engineering based AI goal
– Develop concepts, theory and practice of building
intelligent machines
– Emphasis is on system building
• Science based AI goal
– Develop concepts, mechanisms and vocabulary to
understand biological intelligent behaviours
– Emphasis is on understanding intelligent
behaviours
26
Approaches of AI
• AI can be explained as approaches centered as
both around human and rationality
• The Humanistic-Centered approach
– The scientific part
– Involves an empirical science
– It involves two goals: THNKING AND ACTING
HUMANLY

27
Approaches of AI…
• Humanistic-centered approach
– Thinking Humanly: The Cognitive Modeling
• Reasons like humans do
– Programs that behaves like humans

– Example: Asked to write a program that play chess. Instead of

making the best possible chess-playing program, you would
make one that play chess like people do.

• Requires understanding of the internal activities of the brain

– See how humans behave in certain situations and see if you
could make computers behave in that same way
28
 Approaches of AI…
• Humanistic-centered approach…
– Acting Humanly: The Turing Test
• Can machines think?

• Can machines behave /act/conduct/intelligently?

• Turing Test: Operational test for intelligent behavior

– Do experiments on the ability to achieve human-level performance.

– Acting like humans require AI programs to interact with people

– Suggested major components of AI: Knowledge, reasoning,

language understanding, learning
– “The Turing test contest”– developing a system that pass the Turing
29
test…
 Approaches of AI…
• The Rationalist Approach

• Thinking rationally: The Laws of thought

– A system is rational if it thinks/does the right thing through correct
reasoning

– Aristotle provided that the correct arguments/ thought

structures that gave correct conclusions given correct premises

E.g; Abebe is a man, all men are mortal: therefore Abebe is mortal
– These laws of thought governed the operation of the mind and
initiated the filed of logic

30
Approaches of AI…
• Acting rationally: The rational agent
– Doing the right thing so as to achieve one’s goal,
given one’s beliefs.
– AI is the study and construction of rational agents
(an agent that perceives and acts)
– Rational actions requires the ability to represent
knowledge and reason with it so as to reach good
decision
• Learning for better understanding of how the world
works

31
History of AI
• The concept of intelligent machines is found in
Greek mythology. There is a story in the 8th
century A.D about Pygmalion Olio, the
legendary king of Cyprus. He fell in love with
an ivory statue he made to represent his ideal
woman.
• The king prayed to the goddess Aphrodite, and
the goddess miraculously brought the statue to
life.
32
History of AI
• Other myths involve human-like artifacts. As a
present from Zeus to Europa, Hephaestus
created Talos, a huge robot. Talos was made of
bronze and his duty was to patrol the beaches
of Crete.
• Aristotle (384-322 BC) developed an informal
system of syllogistic logic, which is the basis
of the first formal deductive reasoning system.

33
History of AI
• Early in the 17 th century, Descartes proposed
that bodies of animals are nothing more than
complex machines.
• Pascal in 1642 made the first mechanical
digital calculating machine. In the 19 th century,
George Boole developed a binary algebra
representing (some) "laws of thought."

34
History of AI
• Charles Babbage & Ada Byron worked on
programmable mechanical calculating
machines. In the late 19th century and early
20th century, mathematical philosophers like
Gottlob Frege, Bertram Russell, Alfred North
Whitehead, and Kurt Gödel built on Boole's
initial logic concepts to develop mathematical
representations of logic problems.

35
History of AI
• Formally initiated in 1956 and the name AI was
coined by John McCarthy
• The advent of general purpose computers provided a
vehicle for creating artificially intelligent entities.
• Development of knowledge-based systems: the key to
power
– Performance of general-purpose problem solving methods is
weak for complex domains
– Use knowledge more suited to make better reasoning in
narrow areas of expertise (like human experts do)
– Early knowledge intensive system include:
• The Dendral program (1969): solved the problem of inferring
molecular structure.
• MYCIN (1976): used for medical diagnosis:

36
History of AI…
• Shifts from procedural to declarative
programming paradigm
– Rather than telling the computer how to compute a
solution, a program consists of a knowledge base
of facts and relationships
– Rather than running a program to obtain a solution,
the user asks question so that the system searches
through the KB to determine the answer

37
Limitation of AI today
• Today’s successful AI systems operate in well-
defined domains and employ narrow,
specialized knowledge.
• Common sense knowledge is needed to
function in complex, open-ended worlds. Such
a system also needs to understand
unconstrained natural language.
• However these capabilities are not yet fully
present in today’s intelligent systems.

38
What can AI systems NOT do yet?
– Understand natural language robustly
(e.g., read and understand articles in a news paper)
– Surf the web
– Interpret an arbitrary visual scene
– Learn a natural language
– Construct plans in dynamic real-time
domains
– Exhibit true autonomy and intelligence

39
The Disadvantages
 increased costs
 difficulty with software development - slow and
expensive
 few experienced programmers
 few practical products have reached the market
as yet.
Applications of AI
• AI is concerned with automating both the
Mundane/ordinary and experts tasks.
• Categories of AI applications include:
– Mundane Tasks (Pattern recognition)
– Natural Language Processing (NLP: generation,
translation, understanding)
– Formal Tasks (Games, Puzzles, Mathematics)
– Expert Tasks (Medical Diagnosis, Fault
Finding, Engineering)
– Paradoxically, it turns out that it is the
Mundane task that is generally much the
hardest to automate
41
 Applications of AI…
• Subfields of AI
• Following are major subfields of AI
– Natural Language Processing (NLP)
• It enables computers communicate in human language,
English Amharic…)
– Knowledge Representations (KR)
• Schemas to store information, both facts and inferences,
before and during interrogation
– Automatic Reasoning
• Uses stored information to answer questions and draw
new conclusions

42
Applications of AI…
• Subfields of AI…
– Machine learning
• Adapt to new circumstances and accumulate knowledge
– Computer vision
• Recognize objects based on patterns in the same way as
the human visual system
– Robotics
• Produce mechanical device capable of controlling
motion; which enable computers see, hear and take
actions

43
AI Applications…
Autonomous Planning &
Scheduling:
Autonomous rovers.
AI Applications…
Autonomous Planning & Scheduling:
Telescope scheduling
AI Applications…
Autonomous Planning & Scheduling:
Analysis of data:
AI Applications…
Medicine:
Image guided surgery
AI Applications…
Medicine:
Image analysis and enhancement
AI Applications…
Transportation:
Autonomous vehicle
control:
AI Applications…
Transportation:
Pedestrian detection:
AI Applications…

Games:
AI Applications…
Games:
AI Applications…
Robotic toys:
AI Applications…
Other application areas:

Bioinformatics:
 Gene expression data analysis

 Prediction of protein structure

Text classification, document sorting:

 Web pages, e-mails

 Articles in the news

Video, image classification

Music composition, picture drawing

Natural Language Processing

Perception.
Some Advantages of Artificial Intelligence

 more powerful and more useful computers

 new and improved interfaces
 solving new problems
 better handling of information
 relieves information overload
 conversion of information into knowledge
Famous AI systems that have been developed over the years

• ALVINN

• DEEP BLUE

• MACHINE TRANSLATION

• AUTONOMOUS AGENTS

• INTERNET AGENTS

56
Knowledge Representation & Reasoning
It is the second most important concept in AI

If we are going to act rationally in our environment, then we must have
some way of describing that environment and drawing inferences from that
representation.

 how do we describe what we know about the world ?

 how do we describe it concisely ?

 how do we describe it so that we can get hold of the right piece of

knowledge when we need it ?

 how do we generate new pieces of knowledge ?

 how do we deal with uncertain knowledge ?

 Knowledge

Declarative Procedural

• Declarative knowledge deals with factoid questions (what is

the capital city of Ethiopian? Etc.)

• Procedural knowledge deals with “How”

• Procedural knowledge can be embedded in declarative

knowledge
 Planning
Given a set of goals, construct a sequence of actions that achieves
those goals:

 often very large search space but most parts of the world are
independent of most other parts

 often start with goals and connect them to actions

 what happens if the world changes as we execute the plan

and/or our actions don’t produce the expected results?
 Learning
 If a system is going to act truly appropriately,
then it must be able to change its actions in the
light of experience:
 how do we generate new facts from old ?

 how do we generate new concepts ?

 how do we learn to distinguish different

situations in new environments ?
Interacting with the Environment
 In order to enable intelligent behaviour, we will have to
interact with our environment.

Properly intelligent systems may be expected to:

 accept sensory input vision, sound, …

 interact with humans understand language, recognise

speech, generate text, speech and graphics, …

 modify the environment
 AI Questions

1. Can we make something that is as intelligent as a

human?

2. Can we make something that is as intelligent as a bee?

3. Can we make something that is evolutionary, self

improving, autonomous, and flexible?

4. Can we start a new industry of handwriting, face, retina,

iris and speech recognition agents?
 Assignment I

1. Discuss about Expert System Vs Other Systems

2. Basic Concepts of knowledge base and Intelligent

System

3. Discuss the difference Between AI, Machine

learning and Deep Learning
End of chapter one

64