Introduction to
Intelligent
Computing
Text Book:
Artificial
Intelligence
A Modern Approach
Stuart Russell & Peter
Norvig
Intelligence
• Apple – Newton – Gravity Force
• No one things like him, why should not
apple go towards sky – which one is pulling
towards earth – Earth rotates - force forms
– gravity force.
• Twin tower attack - secret data – Hidden
in image.
• Birbol – without modification make it as
small line – A long line drawn next to the
existing line.
• If a machine has brain – how it will
encounter in new situation.
Approaches to AI
• Systems that act like humans
– The study of how to obtain that computers perform tasks
at which, at the moment, people are better (Rich and
Knight, 1991)
• Systems that think like humans
– The effort to make computers think... machines with
minds in the full and literal sense (Haugeland, 1985)
• Systems that think rationally
– The study of the mental faculties through the study of
computational models (Charniak and McDermott, 1985)
• Systems that act rationally
– The effort to explain and emulate the intelligent behavior
in terms of computational processes (Shalkoff, 1990)
Definitions (Russell + Norvig)
Like humans Not necessarily like humans
Systems that think like Systems that think rationally
humans
Think
Systems that act like Systems that act rationally
humans
Act
5
Human intelligence
• One distinction between these definitions is
whether or not imitating humans is the goal.
• One advantage of imitating humans is that
humans are an easily acknowledged exemplar of
intelligence.
• The Turing Test:
– A human interrogator. Communicates with a hidden
subject that is either a computer system or a human. If
the human interrogator cannot reliably decide whether
on not the subject is a computer, the computer is said
to have passed the Turing test.
6
Turing Test?
In 1950 Turing proposed an
operational definition of
intelligence by using a Test
composed of :
– An interrogator (a
person who will ask
questions)
– a computer (intelligent
machine !!)
– A person who will
answer to questions
A. Turing
– A curtain (separator)
7
What is Artificial
Intelligence?
The computer passes the “test of intelligence” if a human,
after posing some written questions, cannot tell whether
the responses were from a person or not.
8
Turing test
Human intelligence
• Turing provided some very persuasive
arguments that a system passing the
Turing test is intelligent.
• However, the test does not provide
much traction on the question of how
to actually build an intelligent system.
• i.e., Turing test is not enough to see
how a machine acts;
• We also need to know what internal
mental [rational] states it has.
10
Human intelligence
In general there are various reasons
why trying to mimic humans might
not be the best approach to AI.
Computer Human Brain
Computational Units 1 CPU, 108 gates 1011 neurons
Storage Units 1010 bits RAM 1011 neurons
1011 bits disk 1014 synapses
Cycle time 10-9 sec 10-3 sec
Bandwidth 1010 bits/sec 1014 bits/sec
Memory updates/sec 109 1014
11
Eliza (1966)
Conversation with ELIZA,
E> Hello. I am ELIZA. How can I help you?
P> I am feeling sad.
E> I am sorry to hear you are sad.
P> I had some nightmares tonight.
E> You say you had some nightmares tonight?
P> Yes, my dreams are worrying me.
E> What does that dream suggest to you?
P> Thrill, scare.
E> I am not sure I understand you fully.
P> My dreams annoy me.
E> Do you dream often?
P> Yes, daily.
The Chinese room (John
Searle,1980)
Does not necessarily generate
Understanding…
• Human – who understands English, equipped
with a rule book [written in English], various
stacks of paper, some blank, some with
indecipherable[hard to read] inscriptions
[Words].
• Input to room – human finds matching
symbols in the rule book – follows the
instruction.
• From the outside of room – system takes
input in chinese language and generate
answers in chinese language – conventionally
intelligent – turing
Searle argue as follows,
• The person in the room does not
understand Chinese(given), the rule book –
stacks of paper – does not understand
Chinese.
• No understanding of Chinese is going on
• Hence, according to Searle, running the
right program does not necessarily
generate understanding.
Lost in translation
English → Russian (or Spanish)→ English
“The spirit is willing, but the flesh is weak” →
→ Дух охотно готов, но плоть слаба →
→ “The vodka is good, but the meat is rotten”
(Actually: “Spirit is willingly ready, but flesh is weak”
or
“The alcohol is arranged, but the meat is weak”)
Translation requires general knowledge of
language – remove ambiguity.
Autonomous robots
AI Foundations?
AI inherited many ideas, viewpoints and techniques
from other disciplines.
Ps
y ch h y
To olo sop Theories of
investigate g y i lo
human Ph reasoning and
mind learning
AI
Linguistic
Mathematics
The meaning and Theories of logic
structure of probability, decision
language CS making and
computation
Make AI a
reality 18
What is Artificial Intelligence
• To give an answer, the computer would need to
possess some capabilities:
– Natural language processing: To communicate
successfully.
– Knowledge representation: To store what it knows
or hears.
– Automated reasoning: to answer questions and
draw conclusions using stored information.
– Machine learning: To adapt to new circumstances
and to detect and extrapolate patterns.
– Computer vision: To perceive objects.
– Robotics to manipulate objects and move.
19
Goals of AI
AI began as an attempt to understand
the nature of intelligence,
but it has grown into a scientific and
technological field affecting many aspects
of commerce and society.
Solve real-world problems using
knowledge and reasoning.
Creating new opportunities in
business, engineering, and many
other application areas
20
Examples of AI Application
systems
• Game Playing
TDGammon, the world
champion backgammon
player, built by Gerry
Tesauro of IBM research
Deep Blue chess program
beat world champion Gary
Kasparov
Chinook checkers program
21
The decisive game….
““The decisive game of the match was Game
2…we saw something that went beyond
out wildest [Natural] expectations…The
machine refused to move to a position
that had a decisive[crucial] short-term
advantage - showing a very human sense
of danger.”
– Garry Kasparov 1997
Artificial Intelligence History
Early AI: (The gestation of Artificial Intelligence)
1943 McCulloch & Pitts: Boolean circuit model of brain
1950 Turing's ``Computing Machinery and Intelligence''
1950s Early AI programs, including Samuel's checkers
program,
Newell & Simon's Logic Theorist, Gelernter's
Geometry Engine
The birth of Artificial Intelligence (1956)
1956 McCarthy organizes Dartmouth meeting and includes
Minsky, Shannon, Newell, Samuel, Simon
Name ``Artificial Intelligence'' adopted
23
Artificial Intelligence History
Early enthusiam, great expectations (1952-1969):
1957 General Problem Solver [Newell, Simon, Shaw @ CMU]
1958 Creation of the MIT AI Lab by Minsky and McCarthy
1958 LISP, [McCarthy], second high level language (MIT AI
Memo 1)
1963 Creation of the Stanford AI Lab by McCarthy
1965 Robinson's complete algorithm for logical reasoning
A dose of reality (1966-1973):
1966-74 AI discovers computational complexity …
1966-72 Shakey, SRI’s Mobile Robot [Fikes, Nilson]
24
Artificial Intelligence History
Knowledge-based systems (1969-1979)
1969 Publication of “Perceptrons” [Minsky & Papert],
Neural network research almost disappears
1969-79 Early development of knowledge-based systems
1970 SHRDLU, Winograd’s natural language system
1971 MACSYMA, an symbolic algebraic manipulation system
AI becomes an Industry (1980 – present)
1980-88 Expert systems industry booms
1981 Japan: Fifth generation project
US: Microelectronics and Computer Technology Corp.
UK: Alvey
25
Artificial Intelligence History
The return of neural networks (1986 - present)
1988-93 Expert systems industry busts: ``AI Winter''
1985-95 Neural networks return to popularity
AI becomes a science (1987 – present)
1988- Resurgence of probabilistic and decision-theoretic methods
Computational learning theory
``Nouvelle AI'': ALife, GAs, soft computing, emergent
computing …
Complex Systems or the Science of complexity
26
• Rationally – wisely, logically
• Omniscience –knowing everything [om-ni-
science]
• Dichotomy – between two things – the
dichotomy between peace and war [di-cho-
tomy]
• Interrogator – inquiring
• Exemplar - example
• Computational – calculation
• Wildest - natural
• Mental – rational - Internal workings as well as
external behavior
• Conscious – aware - mindful
• Syntactic - syntax
