Introduction to Artificial Intelligence

1
Introduction to Artificial Intelligence
2
Goal of Artificial Intelligence

• Simulate intelligent (human) behavior and/or
  thought processes using computational models
  (computer)
• Understand intelligent entities (reasoning
  mechanisms)
• Build intelligent entities (systems and agents)
• Perceive, understand, predict, and manipulate a
  complex world

3
Approaches to AI

• Horizontal concern, focus of efforts
• thought process and reasoning
• behavior and action
• Vertical evaluation of success
• against human performance
• against ideal concepts of intelligence

Rational behavior do the right thing
4
Think / Act Like Humans

• Cognitive science
• theories of the workings of the human mind
• Comparison of the traces of the reasoning steps

• Creating machines that perform functions that
  require intelligence when performed by humans

• Prove a theorem
• Play chess
• Plan a surgical operation
• Diagnose a disease
• Navigate in a building

5
Turing Test

• Turing Test

After posting some questions, the human
cannot tell whether the responses come from a
person or a computer.

• Natural language processing
• Knowledge representation
• Automated reasoning
• Machine learning

• Total Turing Test

includes a video signal and a physical
object.

• Computer vision
• Robotics

6
Think/Act Rationally

• Always make the best decision given what is
  available
• knowledge, time, resources
• Perfect knowledge, unlimited resources
• logical reasoning
• Imperfect knowledge, limited resources
• (limited) rationality

• Connection to economics, operational research,
  and control theory
• But ignores role of consciousness, emotions,
  fear, etc

7
Foundations of AI
Computer Science and Engineering
hardware, software
8
History of AI
9
Bits of History

• 1956 The name Artificial Intelligence was
  coined.
• Would computational rationality have been
  better?
• Early period (50s to late 60s) Basic
  principles and generality
• General problem solving
• Theorem proving
• Games
• Formal calculus

• AI was stuck
• The spirit is willing but the flesh is weak -gt
  The vodka is good but the meat is rotten
• There has been no machine translation of general
  scientific text, and none is in immediate
  prospect.
• All U.S. government funding for academic
  translation projects was cancelled.

10
Bits of History

• 1969-1971 Shakey the robot (Fikes, Hart,
  Nilsson)
• Logic-based planning (STRIPS)
• Motion planning (visibility graph)
• Inductive learning (PLANEX)
• Computer vision

11
Bits of History

• Knowledge-is-Power period (late 60s to mid
  80s)
• Focus on narrow tasks requiring expertise
• Encoding of expertise in rule formIf the car
  has off-highway tires and 4-wheel drive
  and high ground clearanceThen the car can
  traverse difficult terrain (0.8)
• Knowledge engineering
• 5th generation computer project
• CYC system (Lenat)

12
Bits of History

• AI becomes an industry (80s present)
• Expert systems Digital Equipment, Teknowledge,
  Intellicorp,
• Lisp machines LMI, Symbolics,
• Constraint programming ILOG
• Robotics Machine Intelligence Corporation,
  Adept, ABB,
• Speech understanding

• The return of neural networks (80s 90s)
• genetic algorithms and artificial life
• Increased connection with economics, operational
  research, and control theory (90s present)
• AI becomes less philosophical, more technical and
  mathematically oriented
• Machine Learning and Data Mining

13
Predictions and Reality

• In 1958, Herbert Simon (CMU) predicted that
  within 10 years a computer would be Chess
  champion, which became true in 1997
• Today, computers have won over world champions in
  several games, including Checkers, Othello, and
  Chess but still do not do well in Go

World Chess Champion Garry Kasparov
IBM Deep Blue won 3.5 to 2.5 in Game 6
Kasparov said that he felt a new kind of
intelligence, showing a very human sense of
danger across the board from him.
Saying Deep Blue doesnt really think about
chess is like saying an airplane doesn't really
fly because it doesn't flap its wings.
Drew McDermott
14
Predictions and Reality

• In the 60s, a famous AI professor from MIT said
  At the end of the summer, we will have developed
  an electronic eye
• As of 2002, there is still no general computer
  vision system capable of understanding complex
  dynamic scenes
• But computer systems routinely perform road
  traffic monitoring, facial recognition, some
  medical image analysis, part inspection, etc

15
Predictions and Reality

• In the 70s, many believed that
  computer-controlled robots would soon be
  everywhere from manufacturing plants to home
• Today, some industries (automobile, electronics)
  are highly robotized,
• robots have rolled on Mars, others are performing
  brain and heart surgery
• humanoid robots are operational and available for
  rent
• but home robots are still a thing of the future
  Bicentennial Man

http//world.honda.com/ASIMO/
16
Welcome to the Real World

• Often, the potential of a new field is
  over-estimated in its early age, but
  under-estimated over the longer term
• AI proponents have over-estimated the need for
  smart software, and under-estimated the
  feasibility and potential of large software
  systems based on massive coding effort

• Artificial Intelligence, Matrix,
  Terminator,

17
State of the Art