Pattern Classification: An Introduction

Download Report

Transcript Pattern Classification: An Introduction

Vilalta/Norvig/Eick: History of AI
Origins
McCulloch and Pitts (1943)
Model of Artificial Neurons.
Newell and Simon
General Problem Solver
Donald Hebb (1949)
Hebbian Learning
Conference at Dartmouth (1956)
McCarthy, Minsky, Shannon,
Nathaniel, Samuel (IBM), Solomonoff,
Newell and Simon.
Vilalta/Norvig/Eick: History of AI
Origins
Samuel (1952)
Learning to play checkers
Rosenblatt (1963)
Perceptrons
(convergence theorem)
McCarthy
LISP (1958)
Minsky’s Microworlds (1963)
Blocks world
Simon’s prediction:
“computers will beat a chess champion in 10 years”
“a significant theorem will be proved by a machine”
Vilalta/Norvig/Eick: History of AI
Blocks Worlds
Vilalta/Norvig/Eick: History of AI
Later on…
The knowledge problem.
“the spirit is willing but the flesh is weak”
“The vodka is good but the meat is rotten”
Knowledge based-methods (1969-79)
Buchanan with DENDRAL
(molecular info. from a mass spectrometer)
Expert Systems
MYCIN (diagnose blood infections)
US government funding
was cancelled (1966)
Minksy and Papert
Book Perceptron (1969)
Vilalta/Norvig/Eick: History of AI
AI becomes Industry (1980 – today)
More expert systems.
Systems using Prolog.
After 1988 companies suffered.
Data Mining
Bayesian Networks
Robotics
Computer Vision
AI for the Web
The return of
Neural Networks
Hopfield (1982)
AI becomes Science
neats beat scruffies
Vilalta/Norvig/Eick: History of AI
What is hot in AI --- List of Invited Talks
at the 2004 AAAI/IAAI Conferences
1.
2.
3.
4.
5.
6.
7.
8.
9.
Intelligent Systems and the Nations Vision of Space
Exploration
Agents meet the Semantic Web in the Aether
Real Robots for the Real World
Strength of Character: Personalities in Video Games
Human Dynamics
If not Turing Test, then What?
AI and Biomedicine: Helping Scientists with Genomes, Drugs,
and Diseases
Building a Life Science Company around Statistical Machine
Learning
Applications of Artificial Intelligence to Web Search Peter
Norvig, Google