Download CS440 - Introduction to Artificial Intelligence

Course staff
q 
CS440 - Introduction to
Artificial Intelligence
Instructor: Asa Ben-Hur
n 
n 
n 
q 
Teaching Assistant:
n 
http://xkcd.com/329/
n 
q 
n 
n 
2
Textbook
Web Site: www.cs.colostate.edu/~cs440
What you can find there:
q 
Laura Adams
1
Course website
n 
Office: 448
Office Hours: TBD, or by appt.
Email: asa at cs dot colostate dot edu
n 
All slides (hopefully before class so you can print and take notes
on them)
All homework assignments
RAMCT: only grades
Piazza: discussion board and annoucements
Textbook: S. Russell and
P. Norvig. Artificial
Intelligence: A Modern
Approach. Prentice Hall,
2010, 3rd edition.
3
Workload
n 
n 
n 
4
Grading
Programming/written assignments (~6)
Language: Python
Project
Exams (midterm/final): take home exams
n 
n 
n 
5
Assignments: 40%
Project: 25%
Exams: midterm: 15%
final: 20%
6
1
Course Outline
q 
q 
q 
q 
CSU AI Faculty
Search: How to explore the space of potential
solutions to a problem.
Logic: How to make inferences from stored/
learned knowledge.
Learning: How can a computer learn from data.
n 
Darrell Whitley
Adele Howe
Ross Beveridge
Bruce Draper
n 
Charles Anderson
Machine learning /
computational neuroscience
n 
Asa Ben-Hur
Machine learning in bioinformatics
n 
n 
n 
Genetic algorithms, search problems
Planning
Computer vision (face recognition)
Computer vision (biologically inspired
vision, action recognition, face recognition)
+ brief discussion of other topics
7
What is Artificial Intelligence?
Press View
8
What is Artificial Intelligence?
Movie View
All images are movie posters taken from imdb.com.
What is Artificial Intelligence?
What is AI?
Let’s explore some possible definitions.
Within thirty years, we will have the technological means to create
superhuman intelligence. Shortly after, the human era will be ended.
—"The Coming Technological Singularity" by Vernor Vinge, 1993
12
2
AI: Think Like Humans
n 
AI: Think Like Humans
“The exciting new effort to
make computers think …
machines with minds, in the
full and literal sense”
Haugeland, 1985
n 
How do humans think?
q 
n 
Requires understanding of brain activity (cognitive
model).
The available theories do not explain anything
resembling human intelligence!
13
AI: Act Like Humans
n 
The Turing Test
“The art of creating machines that perform
functions that require intelligence when
performed by people” Kurzweil, 1990
15
The Turing Test
n 
14
http://xkcd.com/632/
Role of the Turing Test
When does a system behave intelligently?
q  Turing (1950) Computing Machinery and Intelligence
q  Operational test of intelligence.
n 
n 
n 
To articulate a performance goal.
To avoid defining intelligence.
How significant is the Turing test?
q 
q 
q 
q 
16
Requires the successful application of major fields of AI:
knowledge representation, reasoning, natural language
processing, machine learning
n 
17
How would you administer it?
What would you ask?
Would we all agree on the outcome?
How close are we?
18
3
IBM’s Watson
AI: Think Rationally
n 
“The study of the computations that make it
possible to perceive, reason, and act.”
Winston 1992
19
Thinking rationally
n 
n 
20
AI: Acting Rationally
Rationality as captured by logic.
n 
Problems:
n 
q 
q 
Not all intelligent behavior is mediated by logical
deliberation
What is the purpose of thinking? What thoughts
should I (bother to) have?
n 
“A field of study that seeks to explain and emulate
intelligent behavior in terms of computation
processes” Schalkoff, 1990
“The branch of computer science that is concerned
with the automation of intelligent behavior” Luger
and Stubblefield
Rational behavior: doing the right thing
q 
n 
The “right thing” is that which is expected to maximize goal
given the available information.
Our focus: rational agents, and how to construct
them.
21
What is AI?
22
Tools
Definitions of artificial intelligence:
Systems that think like
humans
Systems that think
rationally
Systems that act like
humans
Systems that act
rationally
n 
Lisp
n 
Python
n 
Prolog
q 
q 
q 
n 
The traditional AI language
More common in AI research these days
Logic programming: fundamentally different!
The definitions vary by:
q 
q 
Thought processes vs. action
Judged according to human standards vs. success according to an
ideal concept of intelligence.
23
24
4
AI is pervasive in our everyday lives
Application areas
n 
n 
n 
n 
Planning: What to do when.
Computer vision: Seeing is knowing.
Speech recognition: What words are spoken.
Natural language processing (NLP): What do
the words mean.
1. 
2. 
3. 
4. 
5. 
6. 
7. 
8. 
9. 
Check email [spam filter, security agent]
Read news
[personalized information agent]
Drive to work [traffic light control, collision avoidance,
route planning]
Teach [search engine]
Work on research projects [search engine]
Go grocery shopping [market basket analysis, fraud
detection]
Talk with customer service [voice recognition]
Have dinner [search engine]
Watch video [collaborative filtering]
25
AI Systems: Some Milestones
n 
n 
n 
n 
Deep Space 1: AI planner
controls space probe NASA 1999.
Deep Blue: Defeats
Kasparov, Chess Grand
Master - IBM 1997
DARPA grand challenge
2005: 130 mile race of
driverless cars in the
desert.
Curiosity Mars rover 2012
The google driverless car
http://www.grandchallenge.org/
The Curiosity rover
27
AI Technologies: Computer Vision
Image from http://en.wikipedia.org/wiki/Google_driverless_car
28
AI Technologies:
Natural Language Understanding
5
AI Technologies: Robotics
AI in Medicine
Boston Dynamics
DARPA challenge
Texas A&M
Search and rescue
MBARI Fish tracking
Mundane Versus Expert Tasks
n 
Mundane
q 
q 
q 
n 
Foundations of AI
n 
n 
Identifying objects in an image
Answering a question
Picking up an arbitrary object
n 
n 
n 
Expert
q 
q 
q 
q 
n 
Philosophy: Logic, reasoning, rationality.
Mathematics: Logic, computability, tractability
Psychology: understanding how humans think and act.
Neuroscience: how do brains process information?
Economics: theory of rational decisions, game theory.
Computer Engineering: building the hardware and software
that make AI
Chess
Medical diagnosis
Configuring computer hardware (circuit layout)
Special purpose robots
n 
n 
Linguistics: how to deal with language
…
33
Beware of combinatorics!
n 
n 
q 
n 
Foundations of AI: Neuroscience
Use ideas from neuroscience to design
computer architectures that “learn”.
“Solvable in Principle”: little help in practice
Beware of intractability…
q 
34
Considering all possibilities often leads to correct,
but intractable, algorithms.
Intractable means exponential time to solution.
NP-Complete Problems
q 
Class of intractable problems
One View: AI proposes imperfect, but practical,
algorithms to solve NP-Complete problems.
Artist’s depiction of a neural
network
http://www.bitspin.net/images/neuron.jpg
35
Abstraction as an artificial
neural network
http://en.wikipedia.org/wiki/Neural_network
36
6
Primary Areas of AI
n 
n 
n 
n 
n 
n 
n 
n 
n 
Knowledge Representation
Automated Reasoning
Game Playing
Planning
Machine Learning
Search and Optimization
Computer Vision
Robotics
Natural Language Processing
37
7