Artificial Intelligence (AI)

Chapter One

Introduction
 Contents

• Introduction

• AI Vs. KBS

• Views of defining AI

• Strong AI Vs. Weak AI

• History of AI

• State of the Art

• Application of AI
2
• What is Artificial Intelligence ?

05/31/2024 3
Cont’d… AI
• Artificial Intelligence is composed of two words Artificial & Intelligence.
• Artificial defines "man-made," and intelligence defines "thinking power“ or
“the ability to learn
and solve problems”
• So, "It is a 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
Cont’d… AI
Intelligence, as we know, is the ability to acquire and apply knowledge.
Knowledge is the information acquired through experience.
 Experience is the knowledge gained through exposure (past actions,
learning, training).
Therefore, artificial intelligence as the “copy of something natural (i.e.,
human beings) ‘WHO’ is capable of acquiring and applying the information
it has gained through exposure.”
Introduction
 What is intelligence ?
• “The capacity to learn and solve problems” (Webster dictionary)
• The ability to think and act rationally
• Intelligence is the ability of observing, learning, remembering and reasoning
something.

 Which task requires intelligence?

• Complex arithmetic operations
* For instance, Solving 220 * 350?
• Everyday tasks
* Example, Natural language understanding, face recognition
• Expert tasks: which require specialists knowledge
* Example, Medical diagnosis, driving vehicles
Cont.
 What is Artificial Intelligence ?
• AI is a science that tries to develop computer based intelligent systems (entities) that behave as
human
• Basically aims for making the computers which can think intelligently, in the similar manner the
intelligent humans think

 This course focuses on computational intelligence:

• Trying to understand the computational principles behind intelligent behavior

 Top languages for AI

• Python : come with extensive libraries and frameworks and that significantly speed up the
development of complex algorithms.
• Prolog “Programming in Logic,”: is declarative, focusing on the relationship between facts and rules.
Used for developing expert systems, natural language processing, and proving theorems.
• R : a powerhouse for statistical analysis and data visualization(involving heavy data manipulation and
analysis.) used for focusing on the data itself, such as predictive modeling and statistical computing.
• Lisp
• Java
Cont.
 Characteristics of Intelligent system

• Use vast amount of knowledge

• Learn from experience and adopt to changing environment

• Interact with human using natural language and speech

• Understand images (computer vision)

• Respond in real time

• Tolerate error and ambiguity /vagueness/ uncertainity in

Academic Disciplines important to AI.
 AI is a synergy of d/t disciplines
• Psychology/Cognitive Science: how do people behave, perceive, process
information, represent knowledge.
• Neuroscience: neurons as information processing units.
Cont.
• Philosophy: Logic, methods of reasoning, foundations of learning &
rationality.
• Mathematics: Formal representation and proof, algorithms, computation,
probability.
• Computer engineering: building fast computers

• Linguistics: knowledge representation, grammar

AI vs. KBS
 Knowledge based system (KBS) is part of Artificial Intelligence

 What is knowledge ?
 Knowledge includes facts about the real world entities and the relationship
between them
• It is an understanding gained through experience
• Familiarity with the way to perform a task
• An accumulation of facts, procedural rules, or heuristics
Knowledge
 Characteristics of Knowledge:
• It is voluminous (huge) in nature and requires proper structuring.
• It may be incomplete and imprecise.
• It may keep on changing (dynamic).

 AI requires extensive/wide knowledge of the subject at hand.

• AI program should have Knowledge Base
• AI programs should learn in nature and update its knowledge accordingly.
Knowledge Base (KB)
 Knowledge base is centralized repository used to store facts and rules.
 In order to solve problems, the computer needs an internal model of the
world.
• This model contains description of relevant objects and the relations between
these objects.
• All information must be stored in such a way that it is readily accessible.
 Various methods have been used for Knowledge representation, such as
 Logic,
 Semantic networks,
 Frames,
 Scripts, etc...
Knowledge Base System (KBS)
 is a computer program that reasons and uses a knowledge base to solve
complex problem

 KBS - is a form of artificial intelligence (AI) which captures the knowledge

of human experts to support decision-making

 Use inference to solve problems on a computer.

• Inference- is a conclusion reached on the basis of evidence and reasoning.
Views of defining AI
 Four AI Definitions by Russell + Norvig

16
Definition…….

17
 Thinking humanly: The Cognitive
Modeling
 Is concerned with modeling human thinking processes
 The field of cognitive science delves into this topic
• Trying to model how humans think.

 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.

 Example. a program that plays chess like people do

18
Acting humanly: The Turing Test
 Can machines act like human do? Can machines behave intelligently?
 Turing Test:
• Operational test for intelligent behavior (30 min test)
• Is proposed by Alan Turing (1950)
• Do experiments on the ability to achieve human-level performance: can the
evaluator differentiate the response of the human being from the AI program?

19
Thinking Rationally: The Laws of Thought
 A system is rational if it thinks/does the right thing through correct
reasoning.

 Correct premises give correct conclusion

• 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 field of Logic.

20
 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
/notices and acts)

• Rational action 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

21
How to make computers act like humans?
The following sub-fields are emerged

• Natural Language processing - Enable computers communicate in human language,

English, Amharic, …
• 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 does
• Robotics - Produce mechanical device capable of controlled motion, which enable
computers to see, hear & take actions
• Automated reasoning - Use stored information to answer questions and to draw new
conclusions
 Strong AI vs. Weak AI
 Strong AI - Argues that it is possible that one day a computer will be invented
which can be called a mind in its fullest sense.

• Aims to create an agent that can replicate humans intelligence completely; i.e.., it can think,
reason, imagine, etc., and do all the things that we currently associate with the human brain.

 Strong AI refers to a machine that approaches human intelligence

• If it can do typical human tasks
• If it can apply a wide range of background knowledge
• If it has some degree of self-consciousness

 Strong AI aims to build machines whose overall intellectual ability is

indistinguishable from that of human beings

23
Cont.
 Weak AI - On the other hand, argues that computers can only appear to
think and are not actually conscious in the same way as human brains are.
• Try to develop systems which have features of intelligence, but the objective is not to
build a completely conscious entity.
• E.g. like expert systems used for medical diagnosis, speech recognition, chess
program

 Soft AI refers to the use of software to accomplish specific problem solving or

reasoning tasks that do not encompass the full range of human cognitive
abilities
History for AI Developments
 History of AI…….

 Formally initiated in 1956 and the name AI was coined by John

McCarthy.
 The arrival of general purpose computers provided a vehicle for creating
artificially intelligent entities.
 Development of knowledge-based systems
• MYCIN (1976): used for medical diagnosis
 Simulate human mind and learning behavior (Neural Network, Belief
Network, Hidden Markov Models, etc. )

26
Applications of AI
Cont..
 Games: chess, checkers, poker, etc.
 Physical skills: driving a car, driving a motorcycle, flying a plane or
helicopter, playing soccer, vacuuming, etc.
 Art: painting, composing music, performing music, etc.
 Language: machine translation, speech recognition, character recognition,
etc.
 Vision: face recognition, face detection, motion tracking, etc.
 Commerce and industry: page rank for searching, fraud detection, stock
market investing, etc.
 AI Successes

• Deep Blue defeated the leading world chess champion Garry Kasparov in 1997

• Deep Blue was a chess-playing computer developed by

IBM

• First computer chess-playing system to win a chess

match against a ruling world champion under regular
time controls.
Cont.
• Watson - The computer system was initially developed to answer questions
on the quiz show Jeopardy.
• In 2011, the Watson computer system competed on Jeopardy! against
legendary champions Brad Rutter and Ken Jennings winning the first place
prize of $1 million.
 Challenges Ahead
 Note that the examples we discussed so far all involve quite specific
tasks.
 The systems lack a level of generality and adaptability. They can't
easily (if at all) switch context.
 Key issue:
 knowledge acquisition bottleneck
 Lack of general commonsense knowledge.
 Some extra discussion points
1) Discuss one of the following concepts.
i. Knowledge based system:
• What is KBS?
• KBS vs. ES vs. AI
• Knowledge acquisition, knowledge modeling and knowledge representation (semantic
networks, frame, production system, ontology)
ii. Reasoning:
• What is reasoning, Case based reasoning, probabilistic reasoning, fuzzy reasoning, rule-
based reasoning
iii. Learning:
• What is Machine learning? Support Vector Machine, Hidden Markov Model, Bayesian
Belief Network

2) Explain the following areas of AI and how they work ?

i. Natural Language Processing
ii. Natural Language Generation
iii. Speech Recognition, Speech synthesis, Speaker Identification
iv. Optical Character Recognition (OCR),Writer identification, Face recognition
v. Computer vision and robotics 33
Discussion Questions
• What is artificial intelligence?

• How could I apply it in my area of interest?

• How will it change our short term and long-term future?

• What are the challenges and opportunities presented by AI?

 Introduction to AI .....
The End of chapter One

Artificial
Intelligence