Artificial intelligence

Download Report

Transcript Artificial intelligence

Artificial Intelligence
By: Ian, Chelsea, Doug, & Grace
Artificial intelligence (AI) - is a
branch of computer science and
engineering that deals with
intelligent behavior, learning,
and adaptation in machines
History Of Artificial
Intelligence
1950s
• The 1950s were a period of active efforts in AI
• Alan Turing introduced the "Turing test”
• The first working AI programs were written in
1951 to run on the Ferranti Mark I
1960s-1970s
• Joel Moses demonstrated the power of
symbolic reasoning for integration problems
• Leonard Uhr and Charles Vossler published
"A Pattern Recognition Program That
Generates, Evaluates, and Adjusts Its Own
Operators" in 1963
1980s
• Neutral networks became widely used due
to the backpropagation algorithm
• The team of Ernst Dickmanns built the first
robot cars, driving up to 55 mph on empty
streets
• Marked major achievements in many areas
of AI and demonstrations of various
applications
1990s & Turn of the Century
• During the 1990s and 2000s AI has become
very influenced by probability theory and
statistics
• After the September 11, 2001 attacks there
has been much renewed interest and
funding for threat-detection AI systems,
including machine vision research and datamining
DARPA Grand Challenge
• DARPA is a challenge for driverless cars
• The cars have no communication with humans
• In 2005 the winning vehicles completed all 132 miles of the
course in just under 7 hours
A Few Basic Rules
• Must follow California driving laws
• Vehicles must follow a specific rout
following specific check points
• Vehicles must drive though fog and rain
even if GPS is blocked
Schools Of Thought
1. Conventional A.I.
2. Computational
Intelligence
Conventional A.I. - a.k.a.
symbolic A.I., logical A.I., neat
A.I., and Good Old Fashioned
A.I.(GOFAI)
Machine Learning Methods
Expert systems
• a computer program that contains some
subject-specific knowledge of one or more
human experts.
• helps users solve problems and draw
conclusions reasonably.
Machine learning methods
Nuetral Networks
• systems with very strong pattern recognition
capabilities
• a.k.a. ANN (artificial neural network)
• an adaptive system that changes its structure
based on external or internal info that flows
through the network.
Fuzzy Control System
• based on fuzzy logic (concepts that cannot
be expressed as true or false but as partially
true
A.I. In Fiction
• Strong A.I. is used most often for
entertainment purposes
• Usually portrayed as an upcoming power
trying to overthrow human authority
• Trying to cause abrupt and dramatic changes
• A few A.I. writers are: Vernor Vinge, Ray
Kurzweil, and Frank Herbert
• Author Vernor Vinge states, “…technology will
reach a point beyond which we cannot even
speculate about the consequences.”
Case-based Reasoning
• the process of solving new problems
based on the solutions of similar past
problems
Bayesian Network
• a.k.a. Bayesian belief network or belief
network
Behavior Based A.I.
• Made famous by Rodney Brooks
• A procedure for developing A.I. off of
another module of intelligence
Computational Intelligence repetitive development/learning
that relays on evidence
/consequences observable by the
senses
Schools of Thought
• Conventional Artifical Intelligence
– Machine Learning
– Formalism
– Statistical Analysis
•
•
•
•
Expert Systems
Case Based Reasoning
Bayesian Networks
Behavior
Schools of Thought cont.
• Computational Intelligence
– Neural Networkes
– Fuzzy Systems
– Evolutionary Computation
Artifical Intelligence In Fiction
• Books
– A Space Odyssey
– The Moon is a Harsh Mistress
• Movies
– The Matrix
– Bicentennial Man
– I, Robot
• Video Games
– Halo