Artificial Intelligence CIS 342

1
Artificial IntelligenceCIS 342

• The College of Saint Rose
• David Goldschmidt, Ph.D.

January 16, 2007
2
What is Artificial Intelligence?
3
Definitions of Intelligence

• Essential English Dictionary, Collins, London,
  1990
• Ability to understand and learn things
• Ability to think and understand instead of doing
  things by instinct or automatically
• Random House Unabridged Dictionary, 2006
• Capacity for learning, reasoning, understanding
• Aptitude in grasping truths, relationships,
  facts, etc.

4
The Turing Test

• Alan Turing, British mathematician (1912-1954)
• Computing machinery and intelligence paper in
  1950
• Can machines think?
• The Turing Test (a.k.a. Turing imitation game)
• A computer passes the Turing test if human
  interrogators cannot distinguish the machine from
  a human based on answers to their questions

5
The Turing Test

• Turing Test
• Objective standard view on intelligence
• Test is independent of the details of the
  experiment (i.e. numerous variations)
• Provides basis for verification and validation of
  intelligent systems
• Program thought intelligent in some narrow area
  of expertise is evaluated by comparing its
  performance to human performance

6
History of AI

• Warren McCulloch Walter Pitts (1943)
• Research on the human central nervous system led
  to a model of neurons of the brain
• Birth of Artificial Neural Networks (ANN)
• Binary model
• Non-linear model
• John von Neumann
• ENIAC, EDVAC, etc.

7
History of AI

• Claude Shannon, MIT, Bell Labs (1950)
• Computers playing chess
• Chess game involved about 10120 possible moves!
• Even examining one move per microsecond would
  require 3 x 10106 years to make its first move
• Need to incorporate intelligence via heuristics

8
History of AI

• John McCarthy, Dartmouth, MIT (1950s)
• LISP defined
• Only two years after FORTRAN
• Formal logic
• Programs with Common Sense paper (1958)
• Marvin Minsky, Princeton, MIT
• Anti-logical approach to knowledge representation
  and reasoning called frames (1975)

9
History of AI

• Great expectations during 1950s and 1960s
• But very limited success
• Researchers focused too much on all-purpose
  intelligent machines with goals to learn and
  reason with human-scale knowledge (and beyond)
• Refocus on specific problem domains (1970s)
• Domain-specific expert systems with facts, rules,
  etc.
• Analyze chemicals, medical diagnoses, etc.

10
History of AI

• Rebirth of neural networks (1980s-today)
• Adaptive resonance theory (Grossberg, 1980)
  incorporated self-organization principles
• Hopfield networks (Hopfield, 1982)
  introduced neural networks with
  feedback loops
• Back-propagation learning algorithm
  (Bryson
  and Ho, 1969) for training
  multilayer perceptrons

11
History of AI

• Evolutionary computation (1970s-today)
• Natural intelligence is a product of evolution
• Can we solve problems by simulating biological
  evolution?
• Survival of the fittest

12
History of AI

• Knowledge engineering (1980s-today)
• Fuzzy set theory (Zadeh, 1965) associates words
  with degrees of truth or value
• Rule-based knowledge systems
• Combining information from multiple experts
• Semantic Web
• Hybrid approaches abound