Transcript lecture01 - University of Virginia, Department of Computer Science

CS 416
Artificial Intelligence
Lecture 1
Introduction
What is AI?
Discussion exercise for class
• Think of example AI systems (applications that are intelligent)
• Think of example AI Techniques
Textbook
This is a great book
• 2nd edition released one year ago
• Most widely used in U.S. universities
• It’s so good….
– I’m going to make you read it!
Homework
• Read chapters 1 and 2
Syllabus
Instructor
• David Brogan
Olsson 217
982-2211
[email protected]
– Office hours: TBA
TA
• Ben Hocking
– Office hours: TBA
Syllabus
Class web page:
• http://www.cs.virginia.edu/~cs416
Class discussion forum:
• http://www.cs.virginia.edu/~humper/forums/
Grading
• 3 programming assignments (10% each)
• 1 programming project (15%)
• 3 homework assignments (5% each)
• Midterm and Final (20% each)
What is expected of you
You’ll have to do math
• Neural network update function
wi  j  

x ,c T
P x ,c
2wi  j
• Multidimensional function
minimization
• Probability – Bayes’ Rule
• We will teach necessary parts of
statistics and linear algebra
P ( X | Y ) P (Y )
P (Y | X ) 
P( X )
Calculus expected.
Probability and Linear
Algebra beneficial.
What is expected of you
You have to program
• The programming assignments are non-trivial
– C++
– Requires integration with existing code libraries
– Input/output handling (images, for example)
– We do not teach programming in this course
CS 216 expected.
Additional programming
experience beneficial.
Turn in papers
AI Systems
• Thermostat
• Tic-Tac-Toe
• Your car
• Chess
• Google
• Babblefish
• This thing
– Asimo
Examples
• Chess: Deep Junior (IBM) tied Kasparov in 2003 match
ATR’s DB Android
Ritsumeikan University
RHex Hexapod
Honda’s Asimo
AI Techniques
• Rule-based
• Fuzzy Logic
• Neural Networks
• Genetic Algorithms
• Exhaustive search
• Expert Systems
• Logic
How to Categorize These Systems
Systems that think like humans
Systems that act like humans
Systems that think rationally
Systems that act rationally
How to Categorize These Systems
Systems that think/act like humans
It’s hard to study things you can’t observe…
• How can I know how you think?
– Observation is difficult (changing with fMRI). For the most part, you
are a “black box”
– Cognitive Science
• How can I know how you act?
– Observation is possible, but hard to control all aspects of
experimental conditions.
– Turing Test
Alan Turing – “Building a Brain”
World War II motivated computer advances
• Code breaking (1943, Colossus) – Used to decipher
telegrams encrypted using Germany’s encryption machine
• Electronic Numerical Integrator and Computer (ENIAC, 1946)
Turing greatly involved with British efforts to build
computers and crack codes (Bletchley Park)
• Arrested for being a homosexual in 1952 and denied security clearance
• Committed suicide in 1954
Systems that think/act rationally
Rely on logic itself rather than human to
measure correctness
• Thinking rationally (logically)
– Socrates is a human; All humans are mortal; Socrates is mortal
– Logic formulas for synthesizing outcomes
• Acting rationally (logically)
– Even if method is illogical, the observed behavior must be
rational
Perspective of this Course
We will investigate the general principles of
rational agents
• Not restricted to human actions and human environments
• Not restricted to human thought
• Not confined to only using laws of logic
• Anything goes so long as it produces rational behavior
What is AI?
The use of computers to solve problems that
previously could only be solved by applying human
intelligence…. thus something can fit this definition
today, but, once we see how the program works and
understand the problem, we will not think of it as AI
anymore (David Parnas)
Foundations - Philosophy
• Aristotle (384 B.C.E.) – Author of logical syllogisms
• da Vinci (1452) – designed, but didn’t build, first mechanical
calculator
• Descartes (1596) – can human free will be captured by a
machine? Is animal behavior more mechanistic?
• Necessary connection between logic and action is
discovered
Foundations - Mathematics
• More formal logical methods
– Boolean logic (Boole, 1847)
• Analysis of limits to what can be computed
– Intractability (1965) – time required to solve problem scales
exponentially with the size of problem instance
– NP-complete (1971) – Formal classification of problems as
intractable
• Uncertainty (Cardano 1501)
– The basis for most modern approaches to AI
– Uncertainty can still be used in logical analyses
Foundations - Economics
•
Humans are peculiar so define generic happiness term: utility
•
Game Theory – study of rational behavior in small games
•
Operations Research – study of rational behavior in
complex systems
•
Herbert Simon (1916 – 2001) – AI researcher who received
Nobel Prize in Economics for showing people accomplish
satisficing solutions, those that are good enough
Foundations - Neuroscience
How do brains work?
• Early studies (1824) relied on injured and abnormal people to understand what
parts of brain do
• More recent studies use accurate sensors to correlate brain activity to human
thought
– By monitoring individual neurons, monkeys can now control a computer
mouse using thought alone
• Moore’s law states computers will have as many gates as humans have
neurons in 2020
• How close are we to having a mechanical brain?
– Parallel computation, remapping, interconnections, binary vs. gradient…
Foundations - Psychology
• Helmholtz and Wundt (1821) – started to make psychology a
science by carefully controlling experiments
• The brain processes information (1842)
– stimulus converted into mental representation
– cognitive processes manipulate representation to build
new representations
– new representations are used to generate actions
• Cognitive science started at a MIT workshop in 1956 with the
publication of three very influential papers
Foundations – Control Theory
• Machines can modify their behavior in response to the
environment (sense / action loop)
– Water-flow regulator (250 B.C.E), steam engine governor,
thermostat
• The theory of stable feedback systems (1894)
– Build systems that transition from initial
state to goal state with minimum energy
– In 1950, control theory could only describe
linear systems and AI largely rose as a
response to this shortcoming
Foundations - Linguistics
Speech demonstrates so much of human
intelligence
• Analysis of human language reveals thought taking place in
ways not understood in other settings
– Children can create sentences they have never heard
before
– Language and thought are believed to be tightly
intertwined
History of AI
Read the complete story in text
• Alan Turing (1950) did much to define the problems and
techniques
• John McCarthy helped coordinate the players (1956)
• Alan Newell and Herbert Simon (1956) did much to
demonstrate first solutions
• Marvin Minsky (student of von Neumann) built a neural
network (1951) from 3000 vacuum tubes and the “autopilot”
from a B-24 bomber
Why is AI in Computer Science?
• Uses computer as a tool more than psychologists,
mathematicians (operations research), or mechanical
engineers (control theory)
History of AI: 1952- 1969
Great successes!
• Logic programs were replicating human logic in many cases
– Solving hard math problems
– game playing
• LISP was invented by McCarthy (1958)
– second oldest language in existence
– could accept new axioms at runtime
• McCarthy went to MIT and Marvin Minsky started lab at Stanford
– Both powerhouses in AI to this day
History of AI: 1966 - 1973
A dose of reality – Overhyped
• Systems fail to play chess and translate Russian
– Computers were ignorant to context of their logic
– Problems were intractable
 algorithms that work in principle may not work in practice
 Combinatorial Explosion / Curse of Dimensionality
– Fatal flaw in neural networks was exposed
 though flaw was first resolved in 1969, neural networks did not
return to vogue until late 1980s
AI History: 1969 - 1979
Knowledge-based Systems
• Previous systems knocked because general logical
algorithms could not be applied to realistic problems
• Answer: accumulate specific logical algorithms
– DENDRAL – infer chemical structure
– knowledge of scientists boiled down to cookbook logic
– large number of special purpose rules worked well
• Researchers work on ways to accumulate and store facts for
expert systems
AI History: 1980 - present
Let the good times roll
• The demonstrated success of AI invited investments
• from millions to billions of dollars in 10 years
• extravagant AI promises again led to “AI Winter” when
investments in technology dropped (1988)
Neural Networks come back from the dead (1986)
AI History: 1987 - present
AI becomes a science
• More repeatability of experiments
• More development of mathematical underpinnings
• Reuse of time-tested models
Intelligent Agents (1994)
• AI systems exist in real environments with real sensory inputs
• Niches of AI need to be reorganized
AI History: Where are We Now?
• Autonomous planning: scheduling operations aboard a
spacecraft
– Some notable failures (Dante falls in a crater after one
step) and shining successes (Mars Spirit Rover)
• Game playing: Kasparov lost to IBM’s Big Blue in chess
– Rules were changed to prevent computer from retraining
over night and to provide human players with more
examples of computerized play
AI History: Where are We Now?
• Autonomous Control: CMU’s NAVLAB drove from Pittsburgh
to San Francisco under computer control 98% of time
• Logistics: deployment of troops to Iraq
• Robotics: remote heart operations
• human genome, protein folding, drug discovery
• stock market