Intro to Artificial Intelligence and Computer Simulation Instructor Kris Hauser httpcsindianaeduhauserk 1 Basics Class web site http csindianaeduclassesb351 Textbook S Russell and P ID: 582628
Download Presentation The PPT/PDF document "CS B351" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
CS B351: Intro to Artificial Intelligence and Computer Simulation
Instructor: Kris Hauserhttp://cs.indiana.edu/~hauserk
1Slide2
BasicsClass web site
http://cs.indiana.edu/classes/b351TextbookS. Russell and P.
Norvig
Artificial Intelligence: a Modern Approach
3rd edition
2Slide3
BasicsInstructor
Kris Hauser (hauserk@indiana.edu)AIsDan
Coroian
(dcoroian@indiana.edu)
3Slide4
Office HoursKris Hauser
M 2-3,Th 2-3 in Info E 257 (connector building)Dan CoroianTBA
4Slide5
AgendaIntro to AI
Overview of class policies
5Slide6
What is AI?AI is the reproduction of
human reasoning and intelligent behavior by computational methods
6Slide7
What is AI?AI is
an attempt of reproduction of human reasoning and intelligent behavior by computational methods
7Slide8
What is AI?Discipline that systematizes and automates reasoning processes to create machines that:
8
Think like humans
Think rationally
Act like humans
Act rationallySlide9
The goal of AI is: to build machines that operate in the same way that humans thinkHow do humans think?
Build machines according to theory, test how behavior matches mind’s behaviorCognitive ScienceManipulation of symbolic knowledge
How does hardware affect reasoning? Discrete machines, analog minds
9
Think like humans
Think rationally
Act like humans
Act rationallySlide10
The goal of AI is: to build machines that perform tasks that seem to require intelligence when performed by humansTake a task at which people are better, e.g.:
Prove a theoremPlay chessPlan a surgical operation
Diagnose a disease
Navigate in a building
and build a computer system that does it automaticallyBut do we want to duplicate human imperfections?
10
Think like humans
Think rationally
Act like humans
Act rationallySlide11
The goal of AI is: to build machines that make the “best” decisions given current knowledge and resources“Best” depending on some utility function
Influences from economics, control theoryHow do self-consciousness, hopes, fears, compulsions, etc. impact intelligence?Where do utilities come from?
11
Think like humans
Think rationally
Act like humans
Act rationallySlide12
What is Intelligence?
“If there were machines which bore a resemblance to our bodies and imitated our actions as closely as possible for all practical purposes, we should still have two very certain means of recognizing that they were not real men. The first is that they could never use words, or put together signs, as we do in order to declare our thoughts to others… Secondly, even though some machines might do some things as well as we do them, or perhaps even better, they would inevitably fail in others, which would reveal that they are acting not from understanding, …”
Discourse on the Method, by Descartes (1598-1650)
12Slide13
What is Intelligence?Turing Test (c. 1950)
13Slide14
What is intelligence?Slide15
An Application of the Turing Test
CAPTCHA: Completely Automatic Public Turing tests to tell Computers and Humans Apart
15Slide16
Chinese Room (John Searle)
16Slide17
Can Machines Act/Think Intelligently?
Yes, if intelligence is narrowly defined as information processingAI has made impressive achievements showing that tasks initially assumed to require intelligence can be automated
Each success of AI seems to push further the limits of what we consider “intelligence”
17Slide18
Some Achievements
Computers have won over world champions in several games, including Checkers, Othello, and Chess, but still do not do well in Go
AI techniques are used in many systems: formal calculus, video games, route planning, logistics planning, pharmaceutical drug design, medical diagnosis, hardware and software trouble-shooting, speech
recognition
, traffic monitoring,
facial recognition, medical image analysis, part inspection
, etc... DARPA Grand Challenge: robotic car autonomously traversed 132 miles of desert
IBM’s Watson competes with Jeopardy champs
Some industries (automobile, electronics) are highly robotized,
while other robots perform brain
and heart surgery, are rolling
on Mars, fly autonomously, …,
but home robots still remain
a thing of the future
18
18Slide19
Can Machines Act/Think Intelligently?
Yes, if intelligence is narrowly defined as information processing
AI has made impressive achievements showing that tasks initially assumed to require intelligence can be automated
Maybe yes, maybe not, if intelligence cannot be separated from consciousness
Is the machine
experiencing thought?
Strong vs. Weak AI19Slide20
Big Open Questions
Is intelligent behavior just information processing?(Physical symbol system hypothesis)
If so, can the human brain solve problems that are inherently intractable for computers? Will a general theory of intelligence emerge from neuroscience?
In a human being, where is the interface between “intelligence” and the rest of “human nature”
Self-consciousness, emotions, compulsions
What is the role of the body?
(Mind-body problem)20Slide21
21
AI contributes to building an information processing model of human beings, just as Biochemistry contributes to building a model of human beings based on bio-molecular interactions
Both try to explain how a human being operates
Both also explore ways to avoid human imperfections
(in Biochemistry, by engineering new proteins and drug molecules; in AI, by designing rational reasoning methods)
Both try to produce new useful technologies
Neither explains (yet?) the true meaning of being humanSlide22
Main Areas of AI
Knowledge representation (including formal logic)Search, especially heuristic search (puzzles, games)
Planning
Reasoning under uncertainty, including probabilistic reasoning
Learning
Robotics and perceptionNatural language processing
22
Search
Knowledge
rep.
Planning
Reasoning
Learning
Agent
Robotics
Perception
Natural
language
...
Expert
Systems
Constraint
satisfaction Slide23
Bits of History
1956: The name “Artificial Intelligence” is coined
60’s:
Search and games, formal logic and theorem proving
70’s: Robotics, perception, knowledge representation, expert systems
80’s: More expert systems, AI becomes an industry90’s:
Rational agents, probabilistic reasoning, machine learning00’s: Systems integrating many AI methods, machine learning, natural language processing, reasoning under uncertainty, robotics again
23Slide24
AI References
ConferencesIJCAI, ECAI, AAAI, NIPSJournalsAI, Comp. I, IEEE Trans. Pattern Anal. Mach. Intel., IEEE Int. Sys., JAIR
Societies
AAAI, SIGART, AISB
AI Magazine (Editor: IU’s David Leake)
24Slide25
Careers in AI‘Pure’ AI
Academia, industry labsApplied AIAlmost any area of CS!NLP, vision, robotics
Economics
Cognitive Science
25Slide26
Syllabus
Introduction to AIPhilosophy, history, agent frameworksSearchUninformed search, heuristic search,
heuristics, game
playing
Reasoning under uncertaintyProbability, planning under uncertainty, Bayesian networks, probabilistic inference, temporal sequences
Machine learningNeural nets, decision tree learning, support vector machines, etc.Applications
Constraint satisfaction, motion planning, computer vision
26Slide27
Class Policies
27Slide28
PrerequisitesC211
I recommend:Two semesters programmingBasic knowledge of data structuresBasic knowledge of algorithmic complexity
28Slide29
Programming AssignmentsProjects will be written in
PythonEasy to learn2 weeks for each assignmentSee Resources tab on class webpage for helpful links
29Slide30
Grading50
% Homework6 assignments, lowest score will be dropped30% Final15% Midterm
5% Participation
30Slide31
Homework PolicyDue at end of class on due date
Typically ThursdaysNo “slip days”Extensions only granted in rare cases
Require advance notice except emergencies
31Slide32
Final ProjectEncouraged if you are intending to do research or coursework in AI, pursue higher degreeIndividual or small groups (up to 3)
Counts as three homework assignmentsContentSoftware, new research, or technical report
Mid-semester project proposal
End-of-year report and in-class presentationSlide33
TakeawaysAI has many interpretations
Act vs. think, human-like vs. rationalConcept has evolved“Intelligence” has many interpretationsTuring test
Chinese room
AI success stories from each perspective
33Slide34
HomeworkRegister
Textbookhttp://cs.indiana.edu/classes/b351
Readings:
R&N Ch. 1, 26 (introduction and historical perspectives)
R&N 3.1-3
34