01 what is AI

Information about 01 what is AI

Published on January 4, 2008

Author: Kestrel

Source: authorstream.com

Content

Artificial Intelligence: introduction:  Artificial Intelligence: introduction Stefano De Luca Slides mainly by Tom Lenaerts Practical stuff:  Practical stuff Stefano De Luca Mail: [email protected] [email protected] Textbook: S. Russell and P. Norvig Artificial Intelligence: A Modern Approach Prentice Hall, 2003, Second Edition In Italian: Intelligenza artificiale. Un approccio moderno, Utet Exam: written at end and oral If you ask for: intermediate written exam Course overview:  Course overview What is AI. Intelligent agents. Problem solving. Knowledge and reasoning. Logic and logic programming. Prolog. Rule (expert) systems. Jess. Planning Uncertain knowledge and reasoning. Neural Network Genetic Algorithms Industrial case histories Outline :  Outline What is AI A brief history The State of the art (see book) What is Artificial Intelligence :  What is Artificial Intelligence Creative extension of philosophy: Understand and BUILD intelligent entities Origin after WWII Highly interdisciplinary Currently consist of huge variety of subfields This course will discuss some of them Old AI…:  Old AI… Now: Smart Music System:  Now: Smart Music System The Bose uMusic system uses artificial intelligence to learn the listening habits and preferences of its users. Load your CDs into the digital music delivery system, it can hold thousands of songs, and it will learn your listening preferences and prioritize your music collection. Pandora.com:  Pandora.com Control systems:  Control systems What is Artificial Intelligence:  What is Artificial Intelligence Different definitions due to different criteria Two dimensions: Thought processes/reasoning vs. behavior/action Success according to human standards vs. success according to an ideal concept of intelligence: rationality. Systems that act like humans:  Systems that act like humans When does a system behave intelligently? Turing (1950) Computing Machinery and Intelligence Operational test of intelligence: imitation game Test still relevant now, yet might be the wrong question. Requires the collaboration of major components of AI: knowledge, reasoning, language understanding, learning, … Systems that act like humans:  Systems that act like humans Andrew Hodges. Alan Turing, the enigma (Storia di un Enigma, Bollati Boringhieri) Problem with Turing test: not reproducible, constructive or amenable to mathematical analysis. Systems that think like humans:  Systems that think like humans How do humans think? Requires scientific theories of internal brain activities (cognitive model): Level of abstraction? (knowledge or circuitry?) Validation? Predicting and testing human behavior Identification from neurological data Cognitive Science vs. Cognitive neuroscience. Both approaches are now distinct from AI Share that the available theories do not explain anything resembling human intelligence. Three fields share a principal direction. Systems that think like humans:  Systems that think like humans Some references; Daniel C. Dennet. Consciousness explained. M. Posner (edt.) Foundations of cognitive science Francisco J. Varela et al. The Embodied Mind J.-P. Dupuy. The mechanization of the mind Systems that think rationally:  Systems that think rationally Capturing the laws of thought Aristotle: What are ‘correct’ argument and thought processes? Correctness depends on irrefutability of reasoning processes. This study initiated the field of logic. The logicist tradition in AI hopes to create intelligent systems using logic programming. Problems: Not all intelligence is mediated by logic behavior What is the purpose of thinking? What thought should one have? Systems that think rationally:  Systems that think rationally A reference; Ivan Bratko, Prolog programming for artificial intelligence. Systems that act rationally:  Systems that act rationally Rational behavior: “doing the right thing” The “Right thing” is that what is expected to maximize goal achievement given the available information. Can include thinking, yet in service of rational action. Action without thinking: e.g. reflexes. Systems that act rationally:  Systems that act rationally Two advantages over previous approaches: More general than law of thoughts approach More amenable to scientific development. Yet rationality is only applicable in ideal environments. Moreover rationality is not a very good model of reality. Systems that act rationally:  Systems that act rationally Some references Rational agents :  Rational agents An agent is an entity that perceives and acts This course is about designing rational agents An agent is a function from percept histories to actions: For any given class of environments and task we seek the agent (or class of agents) with the best performance. Problem: computational limitations make perfect rationality unachievable. Foundations of AI :  Foundations of AI Different fields have contributed to AI in the form of ideas,viewpoints and techniques. Philosophy: Logic, reasoning, mind as a physical system, foundations of learning, language and rationality. Mathematics: Formal representation and proof algorithms, computation, (un)decidability, (in)tractability, probability. Psychology: adaptation, phenomena of perception and motor control. Economics: formal theory of rational decisions, game theory. Linguistics: knowledge represetatio, grammar. Neuroscience: physical substrate for mental activities. Control theory: homeostatic systems, stability, optimal agent design. A brief history:  A brief history What happened after WWII? 1943: Warren Mc Culloch and Walter Pitts: a model of artificial boolean neurons to perform computations. First steps toward connectionist computation and learning (Hebbian learning). Marvin Minsky and Dann Edmonds (1951) constructed the first neural network computer 1950: Alan Turing’s “Computing Machinery and Intelligence” First complete vision of AI. Idea of Genetic Algorithms A brief history (2):  A brief history (2) The birth of (the term) AI (1956) Darmouth Workshop bringing together top minds on automata theory, neural nets and the study of intelligence. Allen Newell and Herbert Simon: The logic theorist (first nonnumerical thinking program used for theorem proving) For the next 20 years the field was dominated by these participants. Great expectations (1952-1969) Newell and Simon introduced the General Problem Solver. Imitation of human problem-solving Arthur Samuel (1952-)investigated game playing (checkers ) with great success. John McCarthy(1958-) : Inventor of Lisp (second-oldest high-level language) Logic oriented, Advice Taker (separation between knowledge and reasoning) A brief history (3):  A brief history (3) The birth of AI (1956) Great expectations continued .. Marvin Minsky (1958 -) Introduction of microworlds that appear to require intelligence to solve: e.g. blocks-world. Anti-logic orientation, society of the mind. Collapse in AI research (1966 - 1973) Progress was slower than expected. Unrealistic predictions. Some systems lacked scalability. Combinatorial explosion in search. Fundamental limitations on techniques and representations. Minsky and Papert (1969) Perceptrons. A brief history (4):  A brief history (4) AI revival through knowledge-based systems (1969-1970) General-purpose vs. domain specific E.g. the DENDRAL project (Buchanan et al. 1969) First successful knowledge intensive system. Expert systems MYCIN to diagnose blood infections (Feigenbaum et al.) Introduction of uncertainty in reasoning. Increase in knowledge representation research. Logic, frames, semantic nets, … A brief history (5):  A brief history (5) AI becomes an industry (1980 - present) R1 at DEC (McDermott, 1982) Fifth generation project in Japan (1981) American response … Puts an end to the AI winter. Connectionist revival (1986 - present) Parallel distributed processing (RumelHart and McClelland, 1986); back-propagation A brief history (6):  A brief history (6) AI becomes a science (1987 - present) Neats vs. scruffies. In speech recognition: hidden markov models In neural networks In uncertain reasoning and expert systems: Bayesian network formalism … The emergence of intelligent agents (1995 - present) The whole agent problem: “How does an agent act/behave embedded in real environments with continuous sensory inputs” The Hype Cycle of Emerging Technologies (Gartner 2005):  The Hype Cycle of Emerging Technologies (Gartner 2005) Major research areas (Applications):  Major research areas (Applications) Natural Language Understanding Image, Speech and pattern recognition Uncertainty Modeling Expert systems Virtual Reality ….. Symbolic Programming:  Program as Representation of world Symbol as basic element of representation atom, property, relationship Symbolic Expression as method of combination LISP for Symbolic programming PROLOG for logic programming Object-Oriented Concept Symbolic Programming Knowledge Representation:  Knowledge Representation What kind of Knowledge needed for Problem solving ? Structure of knowledge ? declarative vs procedural Representation techniques ? explicit vs (implicit + inference) logic, frame, object-oriented, semantic net, script Knowledge acquisition and update Search Theory:  Search Theory An Optimization method Analyze alternative cases and select one Cope with Exponential complexity, NP classes Try likely one first (Heuristic Search) Utilize local information (Hill Climbing Method) Optimal solution vs good solution Genetic Algorithm, Simulated Annealing Stochastic search Automated Reasoning:  Automated Reasoning Qualitative Reasoning Utilization of qualitative knowledge such as Non-monotonic Reasoning Ostrich flys ? Plausible Reasoning Information fusion under uncertainty Case-based Reasoning Utilization of Experience Machine Learning:  Performance improvement by experience How much of knowledge required to start learning ? Method of acquiring new knowledge and merging it to existing knowledge-base Role of teacher Role of examples and experience Parameter Adjustment Inductive learning Computational Learning Theory Quality of generalization capability in terms of Training data Used in Practice such as Data Mining Machine Learning Data Mining :  Data Mining Data Information / knowledge Decision Making Knowledge extraction for decision making Neural Network:  Computational model of Neurons Power comes from Connection of simple processing element - connectionism S X1 X2 Xn . . . w1 w2 wn F(X1, X2, …, Xn) Neural Network Neural Network:  learning = link weigh adjustment Error-back-propagation : supervised learning Any Functional Mapping is learnable Strong at Sensory Data Processing Symbolic Grounding Old Horse on the race again Massive parallelism, graceful degradation Neural Network Neural Network Classifier:  Neural Network Classifier Input layer Hidden layer Output layer Genetic Algorithms:  Genetic Algorithms Computational model of life evolution Stochastic optimization technique Initial chromosome creation New generations are made (cross over, mutation) survival of the fittest Base of artificial life research study evolution of life, by simulation AI Success Story (Planning):  AI Success Story (Planning) MARVEL (Schwuttke, 1992) Real-time Space shuttle Mission planning Berth assignment (KAL, 1997) Unmanned Vehicle Ground and air Pathfinder Rover, 1996 Asimo – a walking robot Autonomous Land Vehicle (DARPA’s GrandChallenge contest):  Autonomous Land Vehicle (DARPA’s GrandChallenge contest) AI Success Story : Medical expert systems:  AI Success Story : Medical expert systems Antibiotics & Infectious Diseases Cancer Chest pain Dentistry Dermatology Drugs & Toxicology Emergency Epilepsy Family Practice Genetics Geriatrics Programs listed by Special Field Gynecology Imaging Analysis Internal Medicine Intensive Care Laboratory Systems Orthopedics Pediatrics Pulmonology & Ventilation Surgery & Post-Operative Care Trauma Management Pattern Recognition Applications:  Pattern Recognition Applications Handwriting and document recognition forms, postal mail, historic documents PDA pen recognition Signature, biometrics (finger, face, iris, etc.) Gesture, facial expression As a Human computer intertraction EEG, EKG, X-ray Trafic monitoring, Remote Sensing Smart Weapon – guided missile, target homing Handwriting Understanding:  Handwriting Understanding Decision Support Systems (DSS):  Decision Support Systems (DSS) Intelligent Transportation Systems:  Intelligent Transportation Systems Future of AI:  Future of AI Making AI Easy to use Easy-to-use Expert system building tools Web auto translation system Recognition-based Interface Packages Integrated Paradigm Symbolic Processing + Neural Processing AI in everywhere, AI in nowhere AI embedded in all products Ubiquitous Computing, Pervasive Computing Other courses at the UniRoma2:  Other courses at the UniRoma2 AI does not end here … Sistemi di agenti (Specialistica) Cooperazione di Agenti informatici (Specialistica) … Some references:  Some references Understanding Intelligence by Rolf Pfeifer and Christian Scheier. Artificial Intelligence: Structures and Strategies for Complex Problem-solving by George Luger. Computation and Intelligence: Collective readings edited by George Luger. Paradigms of Artificial Intelligence Programming: Case Studies in Common Lisp by Peter Norvig.

Related presentations


Other presentations created by Kestrel

English Literature
16. 02. 2008
0 views

English Literature

birth control
10. 10. 2007
0 views

birth control

ramasetu22may2007 1796
30. 09. 2007
0 views

ramasetu22may2007 1796

purpletree
07. 10. 2007
0 views

purpletree

Verdi
08. 10. 2007
0 views

Verdi

preschool
11. 10. 2007
0 views

preschool

playingwithliterature
12. 10. 2007
0 views

playingwithliterature

mlin2
15. 10. 2007
0 views

mlin2

cartoon pool a d
15. 10. 2007
0 views

cartoon pool a d

J1
16. 10. 2007
0 views

J1

Corps Safety Council 24 Jul 06
18. 10. 2007
0 views

Corps Safety Council 24 Jul 06

reliable multicast
03. 10. 2007
0 views

reliable multicast

Discovery of Cosmic Rays
13. 10. 2007
0 views

Discovery of Cosmic Rays

State of Georgia Sunum
17. 10. 2007
0 views

State of Georgia Sunum

North Africa
23. 10. 2007
0 views

North Africa

slides ch10
01. 11. 2007
0 views

slides ch10

LaoTzu2
04. 12. 2007
0 views

LaoTzu2

drying
07. 12. 2007
0 views

drying

Mikheev SPM210207
15. 10. 2007
0 views

Mikheev SPM210207

benelux intervet 09 12 2004
16. 10. 2007
0 views

benelux intervet 09 12 2004

mpls
29. 10. 2007
0 views

mpls

Network Series Overview
30. 10. 2007
0 views

Network Series Overview

wu zixin defense
01. 11. 2007
0 views

wu zixin defense

Chapter1
02. 11. 2007
0 views

Chapter1

20050812
23. 10. 2007
0 views

20050812

olnes pki interoperability
07. 11. 2007
0 views

olnes pki interoperability

TomGibbs
21. 10. 2007
0 views

TomGibbs

Presentaci n RSC EFQM francais
16. 11. 2007
0 views

Presentaci n RSC EFQM francais

Parts of a Flower
14. 12. 2007
0 views

Parts of a Flower

L1Ch3 2
17. 12. 2007
0 views

L1Ch3 2

dyfi pathfinder presentation
02. 11. 2007
0 views

dyfi pathfinder presentation

Robot
03. 01. 2008
0 views

Robot

2004Summary
03. 01. 2008
0 views

2004Summary

sdocjung e
09. 10. 2007
0 views

sdocjung e

MOM 7
15. 10. 2007
0 views

MOM 7

Do Air Cleaners Work
19. 11. 2007
0 views

Do Air Cleaners Work

transporte maritimo en CA
22. 10. 2007
0 views

transporte maritimo en CA

Wind Hedges905 2 ppt
04. 10. 2007
0 views

Wind Hedges905 2 ppt

richard hansberger
03. 10. 2007
0 views

richard hansberger

EspositoNOW2006
15. 10. 2007
0 views

EspositoNOW2006

Lochbuhler
17. 10. 2007
0 views

Lochbuhler

PRES Canada US Market
29. 10. 2007
0 views

PRES Canada US Market

davereese july99
30. 10. 2007
0 views

davereese july99

884 philmont05 finalpreparations
28. 11. 2007
0 views

884 philmont05 finalpreparations

ch2 voc2
20. 02. 2008
0 views

ch2 voc2

1 74presentation
19. 10. 2007
0 views

1 74presentation

The Causes of War
06. 03. 2008
0 views

The Causes of War

BF CCC conf 2
23. 11. 2007
0 views

BF CCC conf 2

IndustryForumSlidesF eb16
11. 03. 2008
0 views

IndustryForumSlidesF eb16

EAGER UNECE 2007
15. 10. 2007
0 views

EAGER UNECE 2007

spin05 coverity
26. 02. 2008
0 views

spin05 coverity

IM845
24. 03. 2008
0 views

IM845

PresentationAbridged
03. 10. 2007
0 views

PresentationAbridged

chap08 ppt10thedition
08. 04. 2008
0 views

chap08 ppt10thedition

Be Happier Smarter And Healthier
26. 09. 2007
0 views

Be Happier Smarter And Healthier

benefits e
25. 10. 2007
0 views

benefits e

crec ipv6 apan 2
09. 10. 2007
0 views

crec ipv6 apan 2

Cisco Dec4
18. 04. 2008
0 views

Cisco Dec4

Graphplan
30. 10. 2007
0 views

Graphplan

Patoka Final ALS poster
26. 11. 2007
0 views

Patoka Final ALS poster

real options
28. 04. 2008
0 views

real options

Anderson
07. 05. 2008
0 views

Anderson

The Future of Healthcare
08. 05. 2008
0 views

The Future of Healthcare

Lecture22
08. 05. 2008
0 views

Lecture22

prairiechicken
03. 01. 2008
0 views

prairiechicken

PediatricObesityProb lem
30. 04. 2008
0 views

PediatricObesityProb lem

Innovation
02. 05. 2008
0 views

Innovation

PassingGas Dr Railton
02. 05. 2008
0 views

PassingGas Dr Railton

Guide Lines for Bladder Cancer
02. 05. 2008
0 views

Guide Lines for Bladder Cancer

MECH500
02. 05. 2008
0 views

MECH500

l3
23. 11. 2007
0 views

l3

smallpoxmaster
21. 10. 2007
0 views

smallpoxmaster

endeavour 1 00
21. 11. 2007
0 views

endeavour 1 00

backgr
19. 10. 2007
0 views

backgr

Copenhagen
12. 10. 2007
0 views

Copenhagen

presentacion valparaiso
24. 10. 2007
0 views

presentacion valparaiso

ZP582pp
23. 10. 2007
0 views

ZP582pp

pre e301
21. 10. 2007
0 views

pre e301

Riesgo
31. 10. 2007
0 views

Riesgo

Gallick 1 10 07
16. 10. 2007
0 views

Gallick 1 10 07

podcastingagnews
08. 10. 2007
0 views

podcastingagnews

Berton Astronomie par Internet
15. 11. 2007
0 views

Berton Astronomie par Internet

jean michel lauren
11. 04. 2008
0 views

jean michel lauren

Shining Examples 2007
29. 10. 2007
0 views

Shining Examples 2007

lecture9
10. 12. 2007
0 views

lecture9

kathyppt
06. 11. 2007
0 views

kathyppt

Lawrence CAS2K3
28. 12. 2007
0 views

Lawrence CAS2K3

swieta
20. 11. 2007
0 views

swieta