Download AI - Wiki

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

The Talos Principle wikipedia , lookup

Computer vision wikipedia , lookup

Human–computer chess matches wikipedia , lookup

Ethics of artificial intelligence wikipedia , lookup

Computer Go wikipedia , lookup

Philosophy of artificial intelligence wikipedia , lookup

Artificial intelligence in video games wikipedia , lookup

Embodied cognitive science wikipedia , lookup

Transcript
Soccer
• http://youtube.com/watch?v=ICgL1OWs
n58
• http://youtube.com/watch?v=N8Q15Uc
-Ygo
• http://youtube.com/watch?v=1JJsBFiX
Gl0
CIS 197
Computers in Society
Professor John Peterson
Quiz Recap
How does IBM make money with free
software?
Contrast ODF and OOXML
What’s a Turing machine?
What is Lady Lovelace’s objection? How
does it relate to the chess articles?
Why doesn’t Dennett believe people will
consider Deep Blue intelligent?
Slashdot Time
Watch out for Chinese Hackers!
Reading Assignments
For Thursday, the reading is from
Wikipedia.
It’s a little dense but make sure you get
the basic ideas clear before class
Thursday.
Poker
• Did the poker programmers need a
special “super computer” to play a good
game of poker?
• Why would poker be harder to play than
chess?
• What is notable about the computer
strategy in checkers?
• Why are researchers interested in
poker?
• What poker game does Polaris play?
Poker
• What was the format of the
tournament?
• What key aspect of poker was missing?
• What is a “bot”?
• What did the human players think of
the computer opponent?
Soccer
• What sort of players did the CMU team
field in robot soccer?
• What is the stated goal of the robot
soccer movement?
• What is the biggest problem facing the
robots?
• Can humanoid robots move with the
same agility as humans?
• Should we fear a robot rebellion?
Artificial Intelligence
What is it?
What might it be?
Drew McDermott
The Brain As a Computer
• The brain is made up of billions of
neurons
• A neuron is a cell that can send signals
to its neighbors
• The signals depend on inputs from its
neighbors
• Ultimately, input from senses, output to
muscles
What If Each Neuron
Is Computing Something?
Examples:
• Visual cortex: Some neurons match up
images from left and right eyes and
compute the disparities --- the
differences in depth
• Hippocampus: In mice, some neurons
become more active when mouse is in a
particular place (computing degree of
match)
Where is the Mind?
Brai
n
Do some neurons have
“invisible inputs”?
Mind
Is the brain
nothing but a
computer?
Cognitive Science
• An alliance of disciplines: psychology,
philosophy, linguistics, neuroscience,
computer science
• All dedicated to exploring computational
models of mind*
*Within each field, not
everyone is a
“computationalist” about mind
--- yet.
AI
• Within CS, AI is the subdiscipline that
attacks very hard problems using
empirical methods.
• We try algorithms and see how they
work.
• Alas, we have no general theory of
intelligence. We have theories about
language processing, speech recognition,
game playing, plan creation and
execution, robotics, vision, inference, ….
AI Is Not Psychology
• Computationalism in psychology is known as
cognitive psychology.
• It differs from AI in that it is looking for
verification that people’s brains actually
compute what their models say they could
compute.
• It’s less concerned with the details of the
models.
• Experiments with people vs. experiments with
computers.
Computer Vision
• How do you get from an image to
recognition of an object or a person, or
control of object manipulation?
• An image is an array of numbers
(recording light levels). (Compare
retinas.)
• Vision feels easy --- it’s not.
Place Recognition
Where was
this taken?
Remember:
We’re
comparing
arrays of
No two
numbers.
images
are
exactly
the
same.
Solution:
• Adjust for light levels
• Adjust for scale (zoom)
• Find the point where the sum of
differences of light levels is minimal; if
low enough, report “I’ve been here
before!”
Computer Chess
• The best programs can beat almost
every human player
• They do it by searching through game
trees
x
o
x
o
Tic-tac-toe Game Tree
X
x
o
x
x o
o
x o x
X
x o
o x
x o x
o
O
x x o
o
x
O
x
x
o
x
o
o
x
x x o
o o
x
X
x x o
o o
x x
Minimax Algorithm
• Assign numbers to ending positions
(“leaves” of the game tree): 1 if I
(computer) win, -1 if I lose, 0 if draw
• For other nodes of tree, assign number
of minimal child at opponent’s nodes,
maximal child at my nodes
• Choose move with highest number
x
o
x
o
Tic-tac-toe Game Tree
X
x
o
x
x o
o
x o x
X
x o
o x
x o x 1
o
O
x x o
o
x
O
x
x
o
x
o
o
x
x x o
o o
x
X
x x o
o o
x x
x
o
x
o
Tic-tac-toe Game Tree
X
x
o
x
x o
1 o
x o x
X
x o
o x
x o x 1
o
O
x x o
o
x
O
x
x
o
x
o
o
x
x x o
o o
x
X
x x o
o o
x x
x
o
x
o
Tic-tac-toe Game Tree
X
x
1 o
x
x o
1 o
x o x
X
x o
o x
x o x 1
o
O
x x o
o
x
O
x
x
o
x
o
o 1
x
x x o
o o
x x
x x o
o o
x
X
x
o
x
o
Tic-tac-toe Game Tree
X
x
1 o
x
x o
1 o
x o x
X
x o
o x
x o x 1
o
O
x x o
o
x
O
x
x
o
x
o
o 1
x
x x o
o o 0
x
X
x x o
o o -1
x x
x
o
x
o
Tic-tac-toe Game Tree
X
x
1 o
x
x o
1 o
x o x
X
x o
o x
x o x 1
o
O
x x o
0
o
x
O
x
x
o
x
o
o 1
x
x x o
o o 0
x
X
x x o
o o -1
x x
x
o
x
o 1
Tic-tac-toe Game Tree
X
x
1 o
x
x o
1 o
x o x
X
x o
o x
x o x 1
o
O
x x o
0
o
x
O
x
x
o
x
o
o 1
x
x x o
o o 0
x
X
x x o
o o -1
x x
Big Amendment
• In real games, like chess, we can’t look
all the way to the end of the game.
• So we cut the tree off after a few
moves, and use a heuristic evaluation
algorithm to estimate how good the
position is based on board features
(e.g., how many rows I have two of my
marks in vs. how many such rows
opponent has).
• Then apply minimax to pass numbers up.
Real Intelligence?
• Are all the separate subfields of AI going
to achieve real computer intelligence?
• Right now, it depends on what the target
turns out to be. People think their minds
are single entities with general skills, but
we’re discovering more and more
specialized modules in the brain.
• Genius is rare and perhaps unpredictable
Computer Consciousness
• When they build an “artificial nose,” can
it really experience the smell of garlic?
Does it know what turpentine smells
like? Would it have the same
experiences we have?
• Answer: It wouldn’t experience
anything!
But…
• When we know exactly how information
flows through the brain, will we
conclude that we can’t experience
anything?
• Guess: Consciousness will turn out to be
a matter of modeling oneself as having
experiences.
The Self-Modeling Nose
• Suppose the nose is connected to a
robot that can make inferences about
what it thought it smelled and what was
probably there.
• It must distinguish between appearance
and reality. Appearance in this case is
“the way things seem to smell.” At this
point it’s helpful to have the concept of
“odor”
Qualia
• We know what “red” looks like, and how
it differs from “green.” But there’s
nothing much else to say.
• The brain’s theory of itself stops with
these ultimate qualia of things because
it has to stop! Robots will have to do
the same thing (although the details will
differ a lot).
Don’t Get the Wrong Idea…
Most AI people hate to talk about
consciousness. It’s too fuzzy.
This is not what the field is about.
It’s about algorithms and
experimentation.
Summary
• The brain computes things
• Perhaps that’s all it does
• Cognitive science explores this
hypothesis
• AI is the branch that explores
algorithms for difficult computational
problems
• If cognitive science succeeds, it may
even explain consciousness