Scribd
Upload
10 views10 pages

AI Unit01 Ch2a

Great note for AI

Uploaded by

Sourav Samantaray
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views10 pages

AI Unit01 Ch2a

Great note for AI

Uploaded by

Sourav Samantaray
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

ARTIFICIAL

INTELLIGENCE
Russell & Norvig
Chapter 1
What is AI?

Human Rational

Think Cognitive Modeling Laws of Thought/Logic

Act Turing Test Approach Rational Agent Approach


Acting Humanly
• Turing Test Approach (Alan Turing, 1950)
• “Can machines think” à “Can machines behave
intelligently”
• Human interacting with two entities
• How long to tell which is which? How reliable?
• Avoids physical contact
Acting Humanly, continued
• Turing predicted by 2000 a machine would have 30%
chance of fooling a lay person for 5 minutes
• He anticipated all major arguments against AI in following
50 years
• Suggested major components of AI:
• Natural Language Processing
• Knowledge Representation
• Automated Reasoning
• Machine Learning
• Total Turing Test includes Vision and Robotics
• Loebner prize, chatterbot, annual since 1990
• http://en.wikipedia.org/wiki/Loebner_Prize
Thinking Humanly
• Cognitive modeling

• First problem – how do humans think?


• Introspection: catch our own thoughts
• Psychological experiments: observing people
• Brain imaging

• Newell & Simon’s General Problem Solver, 1961


• Less interested in “correct” solutions
• Wanted to compare trace to reasoning steps of human on same
problems
Thinking Rationally
• “Laws of Thought” approach, Logic
• Direct line through math and philosophy to modern A

• Aristotle’s Syllogisms
• For example:
• Socrates is a man man (Socrates)
• All men are mortal ∀x man(x) è mortal(x)
• Then, Socrates is mortal è mortal (Socrates)

• Encode (hard), create database, let inference system


determine valid statements
Acting Rationally
• Rational agent approach
• Agent is something that (perceives and) acts
• Rational agent is one that acts so as to achieve the best
outcome (or best expected outcome, if uncertainty)
• Should make correct inferences (as in Think Rationally) but
also reason logically
• Includes:
• Inference (logic)
• Reflex (hot stove, don’t deliberate)
• Knowledge representation and reasoning
• This is approach used in textbook
Foundations of AI
Philosophy Logic, methods of reasoning, mind as physical system,
foundations of learning, language, rationality
Mathematics Formal representation and proof, algorithms, computation,
decidability, tractability, probability
Psychology Adaptation, perception and motor control, experimental
techniques
Economics Formal theory of rational decisions
Linguistics Knowledge representation, grammar
Neuroscience Mapping brain activity, models of nervous system
Control Theory Stochastic optimal control
History of AI
• Gestation of AI (1943-1955)
• Birth of AI (1956)
• Early enthusiasm, great expectations (1952-1969)
• A dose of reality (1966-1973)
• Knowledge-based systems: key to power (1969-1979)
• AI becomes an industry (1980-present)
• The return of neural networks (1986-present)
• AI adopts the scientific method (1987-present)
• Emergence of intelligent agents (1995-present)
• Availability of very large data sets (2001-present)
AI: State of the Art examples
• Robotic vehicles - driverless
• Speech recognition
• Autonomous planning and scheduling – NASA is leader
• Game playing – IBMs Deep Blue (beat Kasparov, 1997)
• Spam fighting
• Logistics planning – DARPA is leader
• Robotics – Roomba, hazardous materials
• Machine translation – various languages

You might also like