Download Artificial Intelligence

The Foundations of Artificial
Intelligence
Our Working Definition of AI
Artificial intelligence is the study of how to make
computers do things that people are better at or
would be better at if:
• they could extend what they do to a World Wide
Web-sized amount of data and
• not make mistakes.
Why AI?
"AI can have two purposes. One is to use the power of
computers to augment human thinking, just as we use
motors to augment human or horse power. Robotics
and expert systems are major branches of that. The
other is to use a computer's artificial intelligence to
understand how humans think. In a humanoid way. If
you test your programs not merely by what they can
accomplish, but how they accomplish it, they you're
really doing cognitive science; you're using AI to
understand the human mind."
- Herb Simon
A Time Line
View the time line
The Dartmouth Conference and the Name
Artificial Intelligence
J. McCarthy, M. L. Minsky, N. Rochester, and C.E.
Shannon. August 31, 1955. "We propose that a 2
month, 10 man study of artificial intelligence be
carried out during the summer of 1956 at
Dartmouth College in Hanover, New Hampshire.
The study is to proceed on the basis of the
conjecture that every aspect of learning or any
other feature of intelligence can in principle be
so precisely described that a machine can be
made to simulate it."
The Origins of AI Hype
1950 Turing predicted that in about fifty years "an average
interrogator will not have more than a 70 percent chance of
making the right identification after five minutes of
questioning".
1957 Newell and Simon predicted that "Within ten years a
computer will be the world's chess champion, unless the rules
bar it from competition."
Symbolic vs. Subsymbolic AI
Subsymbolic AI: Model
intelligence at a level similar to
the neuron. Let such things as
knowledge and planning emerge.
Symbolic AI: Model such
things as knowledge and
planning in data structures that
make sense to the
programmers that build them.
(blueberry (isa fruit)
(shape round)
(color purple)
(size .4 inch))
The Origins of Subsymbolic AI
1943 McCulloch and Pitts A Logical Calculus of the Ideas
Immanent in Nervous Activity
“Because of the “all-or-none” character of nervous
activity, neural events and the relations among them can
be treated by means of propositional logic”
The Origins of Symbolic AI
• Games
• Theorem proving
Knowledge Acquisition
Hand Crafted
Symbolic
Subsymbolic

Machine Learning


What Are the Components of Intelligence?
Image Perception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Image Perception
But We’re Still Ahead
http://www.captcha.net/
But We’re Still Ahead
But We’re Still Ahead
Reasoning
We can describe reasoning as search in a space of
possible situations.
Recall the 8-Puzzle
Start state
What are the states?
http://www.javaonthebrain.com/java/puzz15/
Goal state
Hotel Maid
States:
Start state:
Operators:
Goal state:
What is a
Heuristic?
Example
From the initial state, move A to the table. Three choices for what
to do next.
A local heuristic function: Add one point for every block that is
resting on the thing it is supposed to be resting on. Subtract one
point for every block that is sitting on the wrong thing.
A New Heuristic
From the initial state, move A to the table. Three choices for what
to do next.
A global heuristic function: For each block that has the correct
support structure (i. e., the complete structure underneath it is
exactly as it should be), add one point for every block in the
support structure. For each block that has an incorrect support
structure, subtract one point for every block in the existing support
structure.
Hill Climbing – Another Example
Problem: You have just arrived in Washington, D.C.
You’re in your car, trying to get downtown to the
Washington Monument.
Hill Climbing – Some Problems
Hill Climbing – Is Close Good Enough?
B
A
Is A good enough?
• Choose winning lottery numbers
Hill Climbing – Is Close Good Enough?
B
A
Is A good enough?
• Choose winning lottery numbers
• Get the cheapest travel itinerary
• Clean the house
The Silver Bullet?
Is there an “intelligence algorithm”?
1957
Start
GPS (General Problem Solver)
Goal
The Silver Bullet?
Is there an “intelligence algorithm”?
1957
GPS (General Problem Solver)
Start
Goal
What we think now:
Probably not
But What About Knowledge?
•Why do we need it?
Find me stuff about dogs who save people’s lives.
•How can we represent it and use it?
•How can we acquire it?
But What About Knowledge?
•Why do we need it?
Find me stuff about dogs who save people’s lives.
Two beagles spot a fire.
Their barking alerts
neighbors, who call 911.
•How can we represent it and use it?
•How can we acquire it?
Expert Systems
Expert knowledge in many domains can be captured as rules.
Dendral (1965 – 1975)
If: The spectrum for the molecule has two peaks at masses x1 and
x2 such that:
• x1 + x2 = molecular weight + 28,
• x1 -28 is a high peak,
• x2 – 28 is a high peak, and
• at least one of x1 or x2 is high,
Then: the molecule contains a ketone group.
To Interpret the Rule
Mass spectometry
Ketone group:
Expert Systems in Medicine
1975 Mycin attached probability-like numbers to rules:
If: (1) the stain of the organism is gram-positive, and
(2) the morphology of the organism is coccus, and
(3) the growth conformation of the organism is clumps
Then: there is suggestive evidence (0.7) that the identity of
the organism is stphylococcus.
Watson
IBM’s site: http://www-03.ibm.com/innovation/us/watson/what-is-watson/index.html
Introduction: http://www.youtube.com/watch?v=FC3IryWr4c8
Watch a sample round: http://www.youtube.com/watch?v=WFR3lOm_xhE
From Day 1 of the real match: http://www.youtube.com/watch?v=seNkjYyG3gI
Bad Final Jeopardy: http://www.youtube.com/watch?v=mwkoabTl3vM&feature=relmfu
Explanation: http://thenumerati.net/?postID=726
How does Watson win? http://www.youtube.com/watch?v=d_yXV22O6n4
Expert Systems – Today: Medicine
Expert systems work in all these areas:
• arrhythmia recognition from electrocardiograms
• coronary heart disease risk group detection
• monitoring the prescription of restricted use antibiotics
• early melanoma diagnosis
• gene expression data analysis of human lymphoma
• breast cancer diagnosis
Dr. Watson
A machine like that is like
500,000 of me sitting at
Google and Pubmed.
http://www.wired.com/wiredscience/2012/10/watson-for-medicine/
But What About Things That All of Us
Know?