Docsity
Docsity

Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity


Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan


Guidelines and tips
Guidelines and tips

Introduction to Artificial Intelligence: Understanding the Basics and History of AI, Study notes of Computer Science

An introduction to artificial intelligence (ai), discussing its definition, operational definitions, and historical context. Various perspectives on ai, including thinking humanly, thinking rationally, and acting humanly or rationally. It also explores the challenges and debates surrounding ai, such as its hard problem status and the turing test. The document also includes a brief history of ai research and its spin-offs, like robotics, computer vision, and neural networks.

Typology: Study notes

Pre 2010

Uploaded on 03/16/2009

koofers-user-rnf
koofers-user-rnf 🇺🇸

10 documents

1 / 33

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Introduction to Artificial
Introduction to Artificial
Intelligence
Intelligence
http://www
http://www-
-courses.cs.uiuc.edu/~cs440/
courses.cs.uiuc.edu/~cs440/
Tuesday and Thursdays
2:00 to 3:15pm, 1404 Siebel Center
Jean Ponce
ponce@cs.uiuc.edu
2065 Beckman Institute
333-8864
pf3
pf4
pf5
pf8
pf9
pfa
pfd
pfe
pff
pf12
pf13
pf14
pf15
pf16
pf17
pf18
pf19
pf1a
pf1b
pf1c
pf1d
pf1e
pf1f
pf20
pf21

Partial preview of the text

Download Introduction to Artificial Intelligence: Understanding the Basics and History of AI and more Study notes Computer Science in PDF only on Docsity!

Introduction to ArtificialIntroduction to Artificial

Intelligence^ Intelligence

http://www^ http://www

  • courses.cs.uiuc.edu/~cs440/-courses.cs.uiuc.edu/~cs440/

Tuesday and Thursdays

2:00 to 3:15pm, 1404 Siebel Center

Jean Ponce

ponce@cs.uiuc.edu

2065 Beckman Institute

TATA

-^

Tuna Oezer (oezer@uiuc.edu)1121 SiebelOffice hours: Mon. 2:00-3:00 and Th. 1:00-2:00.

What is AI?What is AI?

“AI is the study of ideas that enablecomputers to be intelligent.” [P. Winston]So, what is intelligence?^ So, what is intelligence?

  • Fast thinking?• Knowing a lot?• Being able to pass as asmart human?• Being able to reason?
  • Being able to learn?• Being able to perceive andact upon one’s environment?• Writing poetry?• Passing an AI class?

Operational Definitions of AI?Operational Definitions of AI?

Thinking Humanly^ Thinking Humanly `”The automation of activities that we

associate with human thinking,activities such as decision-making,problem solving, learning…” [Bellman, 1978]

Thinking Rationally^ Thinking Rationally “The study of mental faculties through

the use of computational models.” [Charniak & McDermott, 1985]

Acting Humanly ”The study of how to make computers

do things at which, at the moment,people are better.” [Rich& Knight, 1991]

Acting Rationally^ Acting Rationally “The branch of computer science that

is concerned with the automation ofintelligent behavior.” [Luger+Stubblefield, 1993]

Which do we choose?

Acting humanly: The Turing testActing humanly: The Turing test

-^

Predicted that by 2000, a machine might have a 30% chance of foolinga lay person for 5 minutes.

-^

Anticipated all major arguments against AI in following 50 years.

-^

Suggested major components of AI: knowledge, reasoning, languageunderstanding, learning.

-^

Problem: Turing test is not

reproducible, constructive

, or amenable

to

mathematical analysis. Turing (1950) ``Computing machinery and intelligence'':

  • “Can machines think?'' or “Can machines behave intelligently?”• Operational test for intelligent behavior: the Imitation Game.

Thinking rationally: Laws of ThoughtThinking rationally: Laws of Thought^ •^

Aristotle: what are correct arguments/thought processes?

-^

Several Greek schools developed various forms of logic:

Notation

and

rules of derivation

for thoughts.

•^

Direct line through mathematics and philosophy to modern AI.

-^

Problems:1. Not all intelligent behavior is mediated by logical

deliberation.

  1. What is the purpose of thinking? What thoughts should I

have?

Is AI a hard problem?Is AI a hard problem?

  • John drove his sister to buy groceries.• John drove his sister to commit suicide.• John drove his car to commit suicide.• John drove his rabbit to buy groceries.

The meaning of words and sentences^ The meaning of words and sentences

AI PrehistoryAI Prehistory

  • Philosophy• Mathematics• Psychology• Linguistics• Neuroscience• Control Theory

AI History (Cont.)AI History (Cont.)

1969

Publication of “Perceptrons” [Minsky & Papert],Neural network research almost disappears

1969-

Early development of knowledge-based systems

1970

SHRDLU, Winograd’s natural language system

1971

MACSYMA, an symbolic algebraic manipulation system

1980-

Expert systems industry booms

1981

Japan: Fifth generation projectUS: Microelectronics and Computer Technology Corp.UK: Alvey

1988-

Expert systems industry busts: ``AI Winter''

1985-

Neural networks return to popularity

1988-

Resurgence of probabilistic and decision-theoretic methodsComputational learning theory``Nouvelle AI'': ALife, GAs, soft computing

AI research and itsAI research and its

spinoffsspinoffs

Spinoffs

-^

Robotics (ICRA, ISRR, IROS)

-^

Computer Vision (ICCV, CVPR, ECCV)

-^

Neural Networks (NIPS, …)

-^

Machine Learning (MLS, …)

-^

Speech

-^

Natural language understanding

  • AAAI Conference• IJCAI Conference• AI Journal

Graduate studentsGraduate students

-^

Will be graded on a different curve thanundergraduates. They are expected to do better forthe same grade.

-^

May receive ¾ or 1 unit of credit. To receive 1unit they will have to do a programming project,and should contact my before the Spring break sowe can pick a topic.

SyllabusSyllabus

  • Introduction (Ch. 1)• Problem solving and search (Ch. 3)• Informed search methods (Ch. 4)• Logical agents (Ch. 7)• First-order logic and inference (Ch. 8 and 9)• Resolution and planning (Ch. 9 and 11)• Uncertainty (Ch. 13)• Bayesian networks (Ch. 14)• Learning (Ch. 18 and 19)• Neural networks (Ch. 20)• Vision and robotics (Ch. 24 and 25)

Intelligent AgentsIntelligent Agents

  • An

agent

is an entity that perceives and acts.

  • Abstractly, an agent is a function from percept histories toactions: • For any given class of environments and tasks, we seekthe agent (or class of agents) with the best performance.

A

P

f

Designing an agent: (e.g. a taxi)Designing an agent: (e.g. a taxi)

•^

Percept, Action, Goal, Environment (PAGE)

-^

Percepts^ – Video, accelerometers, engine sensors, keyboard, voice,

sound, GPS, …

•^

Actions^ –

Steer, accelerate, brake, horn, speak/display, …

•^

Goals^ –

Safety, reach destination, maximize profits, obey laws,passenger comfort, …

•^

Environment^ – US urban streets, freeways, traffic, pedestrians, weather,

customers, …