CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser...
-
date post
19-Dec-2015 -
Category
Documents
-
view
232 -
download
0
Transcript of CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser...
![Page 1: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/1.jpg)
CS B351: INTRO TO ARTIFICIAL INTELLIGENCE AND COMPUTER SIMULATIONInstructor: Kris Hauser
http://cs.indiana.edu/~hauserk
1
![Page 2: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/2.jpg)
BASICS
Class web site http://cs.indiana.edu/classes/b351
Textbook S. Russell and P. Norvig Artificial Intelligence: a Modern Approach 3rd edition
2
![Page 4: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/4.jpg)
OFFICE HOURS
Kris Hauser M 2-3,Th 2-3 in Info E 257 (connector building)
Dan Coroian TBA
4
![Page 5: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/5.jpg)
AGENDA
Intro to AI Overview of class policies
5
![Page 6: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/6.jpg)
WHAT IS AI?
AI is the reproduction of human reasoning and intelligent behavior by computational methods
6
![Page 7: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/7.jpg)
WHAT IS AI?
AI is an attempt of reproduction of human reasoning and intelligent behavior by computational methods
7
![Page 8: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/8.jpg)
WHAT IS AI?
Discipline that systematizes and automates reasoning processes to create machines that:
8
Think like humans Think rationally
Act like humans Act rationally
![Page 9: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/9.jpg)
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 Science
Manipulation of symbolic knowledge How does hardware affect reasoning?
Discrete machines, analog minds9
Think like humans Think rationally
Act like humans Act rationally
![Page 10: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/10.jpg)
The goal of AI is: to build machines that perform tasks that seem to require intelligence when performed by humans
Take a task at which people are better, e.g.: Prove a theorem Play chess Plan a surgical operation Diagnose a disease Navigate in a building
and build a computer system that does it automatically
But do we want to duplicate human imperfections?
10
Think like humans Think rationally
Act like humans Act rationally
![Page 11: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/11.jpg)
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 theory
How do self-consciousness, hopes, fears, compulsions, etc. impact intelligence?
Where do utilities come from?
11
Think like humans Think rationally
Act like humans Act rationally
![Page 12: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/12.jpg)
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)
12
![Page 13: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/13.jpg)
WHAT IS INTELLIGENCE?
Turing Test (c. 1950)
13
![Page 14: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/14.jpg)
WHAT IS INTELLIGENCE?
![Page 15: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/15.jpg)
AN APPLICATION OF THE TURING TEST CAPTCHA: Completely Automatic Public
Turing tests to tell Computers and Humans Apart
15
![Page 16: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/16.jpg)
CHINESE ROOM (JOHN SEARLE)
16
![Page 17: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/17.jpg)
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 automatedEach success of AI seems to push further the limits of what we consider “intelligence”
17
![Page 18: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/18.jpg)
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
18
![Page 19: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/19.jpg)
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 AI
19
![Page 20: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/20.jpg)
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)
20
![Page 21: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/21.jpg)
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 human
![Page 22: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/22.jpg)
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 perception Natural language
processing22
Search
Knowledgerep.Planning
Reasoning
Learning
Agent
RoboticsPerception
Naturallanguage
... ExpertSystems
Constraintsatisfaction
![Page 23: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/23.jpg)
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
industry 90’s: Rational agents, probabilistic reasoning,
machine learning 00’s: Systems integrating many AI methods,
machine learning, natural language processing, reasoning under uncertainty, robotics again
23
![Page 24: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/24.jpg)
AI REFERENCES Conferences
IJCAI, ECAI, AAAI, NIPS Journals
AI, Comp. I, IEEE Trans. Pattern Anal. Mach. Intel., IEEE Int. Sys., JAIR
Societies AAAI, SIGART, AISB
AI Magazine (Editor: IU’s David Leake)
24
![Page 25: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/25.jpg)
CAREERS IN AI
‘Pure’ AI Academia, industry labs
Applied AI Almost any area of CS! NLP, vision, robotics Economics
Cognitive Science
25
![Page 26: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/26.jpg)
SYLLABUS Introduction to AI
Philosophy, history, agent frameworks Search
Uninformed search, heuristic search, heuristics, game playing
Reasoning under uncertainty Probability, planning under uncertainty, Bayesian
networks, probabilistic inference, temporal sequences
Machine learning Neural nets, decision tree learning, support vector
machines, etc. Applications
Constraint satisfaction, motion planning, computer vision
26
![Page 27: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/27.jpg)
CLASS POLICIES27
![Page 28: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/28.jpg)
PREREQUISITES
C211 I recommend:
Two semesters programming Basic knowledge of data structures Basic knowledge of algorithmic complexity
28
![Page 29: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/29.jpg)
PROGRAMMING ASSIGNMENTS
Projects will be written in Python Easy to learn 2 weeks for each assignment See Resources tab on class webpage for
helpful links
29
![Page 30: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/30.jpg)
GRADING
50% Homework 6 assignments, lowest score will be dropped
30% Final 15% Midterm 5% Participation
30
![Page 31: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/31.jpg)
HOMEWORK POLICY
Due at end of class on due date Typically Thursdays No “slip days”
Extensions only granted in rare cases Require advance notice except emergencies
31
![Page 32: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/32.jpg)
FINAL PROJECT
Encouraged if you are intending to do research or coursework in AI, pursue higher degree Individual or small groups (up to 3)Counts as three homework assignments
ContentSoftware, new research, or technical reportMid-semester project proposalEnd-of-year report and in-class
presentation
![Page 33: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/33.jpg)
TAKEAWAYS
AI has many interpretations Act vs. think, human-like vs. rational Concept has evolved
“Intelligence” has many interpretations Turing test Chinese room
AI success stories from each perspective
33
![Page 34: CS B351: I NTRO TO A RTIFICIAL I NTELLIGENCE AND C OMPUTER S IMULATION Instructor: Kris Hauser hauserk 1.](https://reader033.fdocuments.net/reader033/viewer/2022051618/56649d2f5503460f94a07624/html5/thumbnails/34.jpg)
HOMEWORK
Register Textbook http://cs.indiana.edu/classes/b351 Readings:
R&N Ch. 1, 26 (introduction and historical perspectives)
R&N 3.1-3
34