0% found this document useful (0 votes)
19 views37 pages

Chapter 1 - Introdution

Chapter 1 introduces Artificial Intelligence (AI), defining it as the science of making computers perform tasks that require human-like intelligence. It discusses various approaches to AI, including thinking and acting humanly and rationally, as well as foundational concepts such as learning, reasoning, and perception. The chapter also distinguishes between strong AI, weak AI, and applied AI, highlighting the goals and challenges in developing intelligent systems.

Uploaded by

nataniumcscbe
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
19 views37 pages

Chapter 1 - Introdution

Chapter 1 introduces Artificial Intelligence (AI), defining it as the science of making computers perform tasks that require human-like intelligence. It discusses various approaches to AI, including thinking and acting humanly and rationally, as well as foundational concepts such as learning, reasoning, and perception. The chapter also distinguishes between strong AI, weak AI, and applied AI, highlighting the goals and challenges in developing intelligent systems.

Uploaded by

nataniumcscbe
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 37

Chapter 1

Introduction to AI

1
Outlines
 Introduction to AI
 Objectives/Goals of AI
 What is AI?
 Approaches to AI – making computer:
 Think like a human ( Thinking humanly)
 Act like a human (Acting humanly)
 Think rationally (Thinking rationally)
 Act rationally (Acting rationally)
 The Foundations of AI
 Bits of History and the State of the Art

2
What is AI?
 Artificial Intelligence (AI) is usually defined as the science of making
computers do things that require intelligence when done by humans.
 AI has had some success in limited, or simplified, domains.
 However, the five decades since the inception of AI have brought
only very slow progress, and early optimism concerning the
attainment of human-level intelligence has given way to an
appreciation of the profound difficulty of the problem.
 The term AI is first used by John McCarthy (1956) who considers it
to mean the science and engineering of making intelligent machine.

3
What is Intelligence
 Intelligence is a general mental capability that involves the ability to reason, plan,
solve problems, think abstractly, comprehend ideas and language, and learn.
 Quite simple human behavior can be intelligent yet quite complex behavior performed by
insects is unintelligent.
 What is the difference? Consider the behavior of the digger wasp, Sphex ichneumoneus.
 When the female wasp brings food to her burrow, she deposits it on the threshold, goes
inside the burrow to check for intruders, and then if the coast is clear carries in the food.
 The unintelligent nature of the wasp's behavior is revealed if the watching experimenter
moves the food a few inches while the wasp is inside the burrow checking. On emerging,
the wasp repeats the whole procedure: she carries the food to the threshold once again,
goes in to look around, and emerges. She can be made to repeat this cycle of behavior
upwards of forty times in succession.
 Intelligence--conspicuously absent in the case of Sphex--is the ability to adapt one's
behavior to fit new circumstances.
 Mainstream thinking in psychology regards human intelligence not as a single ability or
cognitive process but rather as an array of separate components.
 Research in AI has focused chiefly on the following components of intelligence:
learning,
4 reasoning, problem-solving, perception, and language-understanding.
Learning
 Learning is distinguished into a number of different forms. The simplest is learning by
trial-and-error.
 For example, a simple program for solving mate-in-one chess problems might try out
moves at random until one is found that achieves mate.
 The program remembers the successful move and next time the computer is given the
same problem it is able to produce the answer immediately. The simple memorizing of
individual items--solutions to problems, words of vocabulary, etc.--is known as rote
learning.
 Rote learning is relatively easy to implement on a computer. More challenging is the
problem of implementing what is called generalization.
 Learning that involves generalization leaves the learner able to perform better in
situations not previously encountered.
 A program that learns past tenses of regular English verbs by rote will not be able to
produce the past tense of e.g. "jump" until presented at least once with "jumped", whereas
a program that is able to generalize from examples can learn the "add-ed" rule, and so
form the past tense of "jump" in the absence of any previous encounter with this verb.
 Sophisticated modern techniques enable programs to generalize complex rules from
data.
5
Reasoning
 To reason is to draw inferences appropriate to the situation in hand.
Inferences are classified as either deductive or inductive.
 Deductive: "Fred is either in the museum or the cafe; he isn't in the cafe; so
he's in the museum",
 Inductive: "Previous accidents just like this one have been caused by
instrument failure; so probably this one was caused by instrument failure".
 The difference between the two is that in the deductive case, the truth of the
premises guarantees the truth of the conclusion, whereas in the inductive
case, the truth of the premises lends support to the conclusion that the
accident was caused by instrument failure, but nevertheless further
investigation might reveal that, despite the truth of the premises, the
conclusion is in fact false.
 There has been considerable success in programming computers to draw
inferences, especially deductive inferences.
 Reasoning involves drawing inferences that are relevant to the task or
situation
6 in hand.
Problem-solving
 Problems have the general form: given such-and-such data, find x. A huge
variety of types of problem is addressed in AI.
 Some examples are: finding winning moves in board games; identifying people
from their photographs; and planning series of movements that enable a robot to
carry out a given task.
 Problem-solving methods divide into special-purpose and general-purpose.
 A special-purpose method is tailor-made for a particular problem, and often
exploits very specific features of the situation in which the problem is embedded.
 A general-purpose method is applicable to a wide range of different problems.
 One general-purpose technique used in AI is means-end analysis, which
involves the step-by-step reduction of the difference between the current state
and the goal state.
 The program selects actions from a list of means--which in the case of, say, a
simple robot, might consist of pickup, putdown, moveforward, moveback,
moveleft, and moveright--until the current state is transformed into the goal
state.
7
Perception
 In perception the environment is scanned by means of various sense-
organs, real or artificial, and processes internal to the perceiver analyze
the scene into objects and their features and relationships.
 Analysis is complicated by the fact that one and the same object may
present many different appearances on different occasions, depending on
the angle from which it is viewed, whether or not parts of it are projecting
shadows, and so forth.
 At present, artificial perception is sufficiently well advanced to enable a
self-controlled car-like device to drive at moderate speeds on the open
road, and a mobile robot to roam through a suite of busy offices searching
for and clearing away empty soda cans.

8
Language-understanding
 A language is a system of signs having meaning by convention. Traffic signs, for
example, form a mini-language, it being a matter of convention that, for
example, the hazard-ahead sign means hazard ahead.
 This meaning-by-convention that is distinctive of language is very different from
what is called natural meaning, exemplified in statements like 'Those clouds
mean rain' and 'The fall in pressure means the valve is malfunctioning'.
 An important characteristic of full-fledged human languages, such as English,
which distinguishes them from, e.g. bird calls and systems of traffic signs, is
their productivity.
 A productive language is one that is rich enough to enable an unlimited number
of different sentences to be formulated within it.
 It is relatively easy to write computer programs that are able, in severely
restricted contexts, to respond in English, seemingly fluently, to questions and
statements, for example the Parry and Shrdlu programs described in the section
Early AI Programs. However, neither Parry nor Shrdlu actually understands
language.
9
Introduction … Cont’d
 AI system possess
 Natural language processing to enable it to communicate
successfully in human language
 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
 Computer vision to perceive objects
 Robotics to manipulate objects and move about
 And others

10
Some Application Areas of AI

11
Cont’d
 Goals of AI
 To Create Expert Systems − The systems which exhibit
intelligent behavior, learn, demonstrate, explain, and advice its
users.
 To Implement Human Intelligence in Machines − Creating
systems that understand, think, learn, and behave like humans

12
Views of defining AI
 Different scholars define AI differently

1. Thinking humanly 2. Acting humanly

3. Thinking rationally 4. Acting rationally

13
AI definition 1: Thinking humanly
• Need to study the brain as an information processing machine:
cognitive science and neuroscience
 AI as systems that think humanly
 “The automation of activities that we associate with human thinking,
activities such as decision-making, problem solving, learning …”
(Bellman definition, 1978)
 “The exciting new effort to make computers think … machines with
minds, in the full and literal sense” (Haugeland definition, 1985)

14
Thinking humanly: Cognitive modeling
 How human thinks ?
• We need to get inside the actual workings of human minds
• There are three ways to do this:
• through introspection—trying to catch our own thoughts as they go by;
• through psychological experiments—observing a person in action;
• and through brain imaging—observing the brain in action
 Can we build a brain?
 Requires:
 Scientific theories of internal activities of the brain
 How to validate a given agent think humanly?
 The answer Requires either
1. Predicting and testing the behavior of human subjects from his/her thinking point of view (top-down)
or
2. Direct identification from neurological data (bottom-up)
 The interdisciplinary field of cognitive science brings together computer models from AI
and experimental techniques from psychology to construct precise and testable theories of
the human mind
 Computational modeling uses simulations to study how human intelligence may be
structured
 Study on Mental processing logic of human being (cognitive science) is not yet fertile
15
AI definition 2: Acting humanly
 “The art of creating machines that perform functions that require
intelligence when performed by people.” (Kurzweil definition,
1990)
 “The study of how to make computers do things at which, at the
moment, people are better.” (Rich and Knight definition, 1991)

16
Acting humanly: Turing Test
 Turing (1950) on his famous paper "Computing machinery and
intelligence":
 "Can machines think?"  "Can machines behave intelligently?"
 Operational test for intelligent behavior: the Imitation Game

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


a person for 5 minutes
Anticipated all major arguments against AI in following 50 years
Active areas of research to achieve this: Machine learning, NLP,
Computer vision, etc
Focus is on action , and not intelligent behavior
17
The goal is to develop systems that are human-like
The Turing Test
• Loebner prize
 2008 competition: each of 12 judges was given five minutes to
conduct simultaneous, split-screen conversations with two hidden
entities (human and chatterbot). The winner, Elbot of Artificial
Solutions, managed to fool three of the judges into believing it was
human [Wikipedia].

18
AI definition 3: Thinking rationally
 A system is said to be rational if it does the “right thing” given
what it knows.
 “The study of mental faculties through the use of computational
models.” (Charniak and McDermott definition, 1985)
 “The study of the computations that make it possible to perceive,
reason, and act.” (Winston definition, 1992)

19
Thinking rationally: "laws of thought"
 Right thinking is related to irrefutable reasoning process
 Require structure that always gave correct conclusion given correct
premises
 Logic is the key to design and implement an agent that think rationally
 Several Greek schools developed various forms of logic: notation and
rules of derivation for thoughts;
 Direct line through mathematics and philosophy to modern AI
• Logic: patterns of argument that always yield correct conclusions when
supplied with correct premises
 “Socrates is a man; all men are mortal; therefore Socrates is
mortal.”
 The 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
20
AI definition 3: Thinking rationally
• Logicist approach to AI: describe problem in formal logical notation
and apply general deduction procedures to solve it
• Problems with the logicist approach
 Computational complexity of finding the solution
 Describing real-world problems and knowledge in logical notation
 Dealing with uncertainty
 A lot of “rational” behavior has nothing to do with logic

21
AI definition 4: Acting rationally
 “Computational intelligence is the study of the design of intelligent
agent” (Poole, et al definition, 1998)
 “AI … is concerned with intelligent behavior in artifacts.”
(Nilsson definition, 1998)
 The course advocates to agents that act rationally

22
Acting rationally: rational agent
 A rational agent is one that acts so as to achieve the best outcome or,
when there is uncertainty, the best expected outcome
 In this approach, AI is viewed as the study and construction of rational
agent
 Rational behavior: doing the right thing
 The right thing: is the action/decision which is expected to maximize goal
achievement, given the available information
 Doesn't necessarily involve thinking
 One way of acting rationally is to reason logically to the action.
 This indicates, making correct inference is part of being a rational agent
 But rationality doesn’t require correct inference because some time
without having correct thing to do, agent must act rationally
 Rational agent has two advantages over other approaches:
 It is more general than the “laws of thought” approach because correct inference
is just one of several possible mechanisms for achieving rationality
 It is more amenable to scientific development than are approaches based on
human behavior or human thought
 Goal is to develop systems that are rational and sufficient
23
Introduction cont’d
 Strong AI:
 aims to build machines that can truly reason and solve problems
 These machines should be self aware and their overall intellectual ability needs to be
indistinguishable from that of a human being
 Strong AI maintains that suitably programmed machines are capable of cognitive mental
states
 Weak AI:
 deals with the creation of some form of computer-based artificial intelligence that cannot
truly reason and solve problems, but can act as if it were intelligent.
 Weak AI holds that suitably programmed machines can simulate human cognition
 Applied AI:
 aims to produce commercially viable "smart" systems such as, for example, a security system
that is able to recognize the faces of people who are permitted to enter a particular building.
 Applied AI has already enjoyed considerable success.
 Cognitive AI:
 computers are used to test theories about how the human mind works—for example, theories
about how we recognize faces and other objects, or about how we solve abstract problems

24
Utility maximization formulation
• Advantages
 Generality: goes beyond explicit reasoning, and even human
cognition altogether
 Practicality: can be adapted to many real-world problems
 Naturally accommodates uncertainty
 Amenable to good scientific and engineering methodology
 Avoids philosophy and psychology

• Disadvantages?

25
Introduction … Cont’d
 AI follows all the four approach but tension existing between
approaches which are centered around human and rationality.
 Human centered approach must be empirical science, involving
hypothesis and experimental confirmation.
 A rationalist approach involves a combination of mathematics
and engineering
 This course focus on the study of a rational agent that think and
act rationally.

26
AI prehistory
 Philosophy Logic, methods of reasoning, mind as
physical system foundations of learning,
language, rationality
 Mathematics Formal representation and proof
algorithms, computation, (un) decidability,
(in) tractability, probability
 Economics Decision theory
 Neuroscience physical substrate for mental activity
 Psychology phenomena of perception and motor
control, experimental techniques,
 cognitive science
 Computer building fast computers
engineering
 Control theory design systems that maximize an objective
function over time
 Linguistics knowledge representation, syntax,
27 grammar
History of AI
 Warren McClloch and Walter Pitts (1943)
 1st AI work: Boolean circuit model of the brain
 Drew on three sources
1. Knowledge of the basic physiology and function of neurons in the brain
2. The formal analysis of propositional logic due to Russell and Whitehead
3. Turing’s theory of computation
 They proposed a model of artificial neurons
 They showed any computable function could be computed by some
network of connected neurons
 They also suggested that suitably defined networks could learn
 Donald Hebb (1949) demonstrated a simple updating rule for modifying the
connection strengths between neurons. His rule, now called Hebbia learning,
remains an influential model to this day
 Alan Turing’s vision was perhaps the most influential. In his article “
Computing Machinery and Intelligence” in 1950, he also introduce Turing
Test,machine learning, genetic algorithms, and reinforcement learning

28
History of AI
 Claude Shannon (1950) and Alan Turing (1953)
 Write a chess program

• Marvin Minisky and Dean Edmonds (1951)


 Built the 1st neural network computer

29
History of AI Cont..
 Newell and Simon develop a reasoning program called
the Logic Theorist (LT) before Dartmouth workshop
 They then come up with the General Problem Solver
(GPS)
 GPS, unlike LT, is designed to imitate human problem
solving protocols and it is the 1st program to embody the
“thinking humanly” approach of AI
 Herbert Gelernter, 1959 constructed the Geometry
Theorem Prover (GTP), which was able to prove theorems
that many students of mathematics would find quite tricky

30
History of AI Cont..

 Arthur Samuel, 1952 wrote a series of checker programs


 It can learn, which disprove the idea that computer
can only do what they are told to do
 His program play better than the creator

 John McCarthy, 1958 at MIT


 Define the 2nd old high level programming language,
LISP which is the 1st and dominant AI programming
language
 Invent time sharing concept with his friend to avoid
the problem of time as a resource.
31
History of AI Cont..
 1958 is also marked the year that Marvin Minisky moved
to MIT
 Minisky supervised a series of students who choose
limited problems that appeared to require intelligence to
solve (this problems known as Micro world)
 The most dominant micro world problem is the block
world
 It consists of a set of solid blocks placed on top of the
table
 A typical task in this world is to rearrange the blocks in a
certain way, using a robot hand that can pick up one block at
a time.

32
Cont’d
 Knowledge-based systems: The key to power? (1969–1979)
DENDRAL program (Buchanan et al., 1969)
The significance of DENDRAL was that it was the first successful knowledge-intensive system: its
expertise derived from large numbers of special-purpose rules
• Feigenbaum, Buchanan, and Dr. Edward Shortliffe developed
MYCIN to diagnose blood infections. With about 450 rules, MYCIN was able to perform as well as some
experts, and considerably better than junior doctors.
It also contained two major differences from DENDRAL
• unlike the DENDRAL rules, no general theoretical model existed from which the MYCIN rules
could be deduced They had to be acquired from extensive interviewing of experts, who in turn
acquired them from textbooks, other experts, and direct experience of cases.
• the rules had to reflect the uncertainty associated with medical nowledge
 The emergence of intelligent agents (1995–present)
• AI systems have become common in Web-based applications that the “-bot” suffix has entered
everyday language
• Moreover, AI technologies underlie many Internet tools, such as search engines, recommender systems,
and Web site aggregators.

33
Cont’d
 The availability of very large data sets (2001–present)
• One influential paper in this line was zarowsky’s (1995) work on word-sense
disambiguation: given the use of the word “plant” in a sentence, does that refer to
flora or factory?
• Hays and Efros (2007) discuss the problem of filling in holes in a photograph
 AI becomes an industry(1980-present)
• The first successful commercial expert system, R1, began operation at the Digital
Equipment Corporation (McDermott, 1982).
• The program helped configure orders for new computer systems; by 1986, it was
saving the company an estimated $40 million a year.
• In 1981, the Japanese announced the “Fifth Generation” project, a 10-year plan
to build intelligent computers running Prolog.
• In response, the United States formed the Microelectronics and Computer
Technology Corporation (MCC) as a research consortium designed to assure
national competitiveness

34
Summary on history of AI
 1943 McCulloch & Pitts: Boolean circuit model of brain
 1950 Turing's "Computing Machinery and Intelligence"
 1956 Dartmouth meeting: "Artificial Intelligence" adopted
 1952—69 Look, Ma, no hands!
 1950s Early AI programs, including Samuel's checkers
program, Newell & Simon's Logic Theorist,
Gelernter's Geometry Engine
 1965 Robinson's complete algorithm for logical reasoning
 1966—73 AI discovers computational complexity
Neural network research almost disappears
 1969—79 Early development of knowledge-based systems
 1980-- AI becomes an industry
 1986-- Neural networks return to popularity
 1987-- AI becomes a science
 1995-- The emergence of intelligent agents
35
AI state of the art
 What can AI do today?
 Some application of AI
 Robotic vehicles
 Speech recognition
 Autonomous planning and scheduling
 Game playing
 Spam fighting
 Logistics planning
 Robotics
 Machine Translation

36
 Reference
Russell, S. and P. Norvig (1995) Artificial Intelligence: A Modern
Approach Prentice-Hall.

37

You might also like