dzitac ia print-1

7/26/2019 Dzitac Ia Print-1

1/190

I O A N D Z I A C

I N T E L I G E N A R T I F I C I A L

2008


2/190

Ioan Dziac, Inteligen artificial, 2008II

Titlul crii: INTELIGEN ARTIFICIALBook title:ARTIFICIAL INTELLIGENCE

Descrierea CIP a Bibliotecii Naionale a Romniei

DZIAC, IOANInteligen artificial / Ioan Dziac. - Arad : Editura

Universitii Aurel Vlaicu, 2008ISBN 978-973-752-292-4

004.42

Ioan Dziachttp://dzitac.rdsor.ro

Domenii principale de interes:Calcul paralel i distribuit, Inteligen

artificial, Metode fuzzy i neuro-fuzzy

Ioan Dziac, Miu-Jan Manolescu,Lotfi A. Zadeh, Florin Gheorghe Filip

Ioan DZIAC(n. 14.02.1953, Poienile de subMunte, Maramure), este absolvent alFacultii de Matematic i Informatic alUniversitii Babe-Bolyai din Cluj-Napoca(1977), unde a obinut i titlul doctor ninformatic (2002) cu teza Procedee de calcul

paralel i distribuit n rezolvarea unor ecuaiioperatoriale.n perioada 1977-1991 a predat matematic nnvmntul preuniversitar, obinnd titlul deprofesor evideniat n 1988 i gradul didacticI cu lucrarea Utilizarea calculatorului npredarea - nvarea matematicii (1990).n perioada 1991-2003 a ocupat prin concursun post de lector universitar la Universitateadin Oradea, iar apoi cel de confereniaruniversitar (2003-2005). n perioada 2004 -2005 a fost directorul Departamentului deMatematic i Informatic al Universitii dinOradea. n prezent este confereniar universitar

i directorul centrului de cercetare Tehnologiiinformatice avansate n management iinginerie la Universitatea Agora din Oradea,unde a fondat n 2006, alturi de acad. F.G.Filip i prof. Miu-Jan Manolescu, revistaInternational Journal of Computers,Communications and Control, prima revistromneasc de Computer Science cotat ISIWeb of Science (ncepnd cu numrulsuplimentar din 2006).

A fondat conferinaInternational Conference Computers, Communications and Control(ICCCC 2006), care la ediia ICCCC 2008 s-a bucurat de prezena printelui mulimilor i alogicii fuzzy, Lotfi A. Zadeh, alturi de care a editat cartea

Lotfi A. Zadeh, Dan Tufis, Florin Gheorghe Filip, Ioan Dzitac (eds.), From NaturalLanguage to Soft Computing: New Paradigms in Artificial Intelligence , Editura AcademieiRomne, ISBN:978-973-27-1678-6, 2008 .


3/190

Ioan Dziac, Inteligen artificial, 2008 III

PREFA

nva de la toate...(Din lirica norvegian)

1. De ce n titlul crii apare Inteligen artificial i nu Inteligenaartificial?

Rspunsul este simplu: a doua variant ar putea sugera o abordareexhaustiv a Inteligenei Artificiale (IA), ceea ce ar fi prea ambiios i dificil.Aici ne vom limita doar la un studiu introductiv n IA. Vom face o incursiunesuperficial (i inegal), fr a intra n amnunte tehnice ale tuturor domeniilori subdomeniilor IA. Vom insista mai mult pe aspectele care implic logicafuzzy, deoarece raionamentul bazat pe acest nou tip de logic (nuanat) a

deschis noi perspective n soluionarea problemelor pentru care nu dispunem demodele matematice exacte.

2. Care este scopul acestei cri i cui se adreseaz?

Prezenta carte se adreseaz n primul rnd studenilor de la programul destudii de licen, anul III, de la Universitatea Aurel Vlaicu din Arad,Facultatea de tiine Exacte, servindu-le drept suport de curs, dar poate fi utiloricrui cititor care dorete s se familiarizeze cu preocuprile i aplicaiile IA.

Cartea este scris cu scopul declarat de a trezi interesul studenilor, i nunumai, pentru studiul IA, ca studiu independent sau n cadrul unor programe

licen, masterat i doctorat din nvmntul superior, motiv pentru care vasemna pe alocuri mai mult cu o carte de popularizare a tiinei dect cu olucrare tiinific propriu-zis. Aceast abordare are o dubl motivaie: primaeste de natur didactic n spiritul principiului accesibilitii, iar a doua estede natur metodologic n spiritul familiarizrii cu metodele de lucru cunoiuni imprecise, specifice soft computing-ului.

3. Ce este IA?

Dac vei pune aceast ntrebare la 10 informaticieni, vei primi 10rspunsuri diferite. Cert este c IA, ca ramur tiinific, se poate ncadra n

clasa mai larg a informaticii/tehnologiei informaiei/tiinei calculatoarelor(nici ntre aceste 3 tiine nu exist o delimitare clar i uneori se folosesc casinonime). Dar, vom vedea c IA este o tiin interdisciplinar, chiar


4/190

Ioan Dziac, Inteligen artificial, 2008IV

multidisciplinar, implicnd rezultate din alte tiine ca matematica, biologia,psihologia, filozofia etc. IA ncearc s imite inteligena natural.

Pentru a evita discuiile teoretice, de natur filozofic, asupra sensului saunonsensului IA, ni se pare mai productiv s utilizm atributul artificial ncoresponden strict cu atributul natural(Brbat, 2002), pentru a desemna oentitate elaborat de om care imit, mai mult sau mai puin, o entitate

corespondent care exist i n natur. De exemplu, mierea produs de albineexist n natur, este un produs natural i o numim miere natural (miere dealbine), dar exist i miere artificial, fabricat de om.Atributul artificialnuse utilizeaz pentru produse care nu exist i n natur. De exemplu, telefonulnu este un produs artificial, dei este produs de om, deoarece nu exist telefoaneproduse pe cale natural (ns telefonul poate avea n componena sa elementeinteligente).

Vom utiliza sintagma inteligen artificial pentru a desemna clasaunor produse concepute de om (sisteme, ageni, programe de calculator, maini,automate, roboi, etc.), care imit inteligena natural: creierul uman, reeauaneuronal, membrana celulei, inteligena comportamental emergent

grupurilor sociale non-umane (colonii de furnici, roiuri de albine, stoluri depsri, bancuri de peti, haite de lupi etc.) i altele.

4. De unde am cules informaia?

Aceast carte este un studiu bazat pe alte cri i articole tiinifice, studiutrecut prin filtrul autorului i actualizat, pe ct posibil, fa de crile dereferin. Este ceea ce se numete ndeobte un curs de autor. Dar, chiar ntimp ce scriu aceast carte apar alte nouti n IA, ca urmare invit cititorii s-iactualizeze singuri noutile din tot mai multe surse web demne de ncredere.

Am folosit n documentare n mod special cartea [Br02], n limba

romn, Sisteme inteligente orientate spre agent, scris de Boldur E. Brbat(Ed. Academiei, 2002), precum i cartea [RuN03], n limba englez, ArtificialIntelligence: A Modern Approach, scris de Stuart Russell i Peter Norvig (ed. aII-a, Prentice Hall 2003), mprosptnd informaia cu alte surse, cri i revisteexistente n biblioteci reale i virtuale (lista complet a surselor de informaieeste precizat n bibliografie sau/i n notele de subsol).

Am lsat multe cuvinte i expresii netraduse din limba englez, fie c nuam putut gsit traducerea potrivit, fie c am considerat c cititorii ar trebui scunoasc limba englez.

Recomand cu cldur cele dou cri i cititorilor care vor s afle maimulte despre IA, precum i celelalte surse bibliografice i webografice.

Ioan Dziac


5/190

Ioan Dziac, Inteligen artificial, 2008 V

CUPRINS

O INTRODUCERE SUMAR N IA1. CE este IA? Testul Turing, cuvinte i sintagme cheie

2. DE CE studiem, cercetm i producem IA?3. UNDE se studiaz, cerceteaz i promoveaz IA ?4. CINE? Autori, conductori de doctorate, cercettori5. CUM? Metode, modele, mijloace, tehnologii

12

341226

CAPITOLUL 1. INTELIGENA ARTIFICIAL CA IMITAIEAPROXIMATIV A INTELIGENEI NATURALE

1.1. Inteligena natural uman1.1.1. Generaliti1.1.2. Inteligene multiple1.1.3. Inteligena cognitiv (IQ). Teste psihometrice pentru IQ1.1.4. Inteligena emoional (EQ). Inteligena social

1.2. Inteligena natural emergent grupurilor sociale de animale(Swarm Intelligence)

1.3. Inteligena artificial (IA)1.3.1. Definiii. Testul Turing1.3.2. Obiectul de studiu al IA1.3.3. Istoricul IA1.3.4. Domeniile de cercetare i aplicaie ale IA

1.3.4.1. Raionamentul logic1.3.4.2. Reprezentarea cunoaterii1.3.4.3. Percepia1.3.4.4. Calcul evolutiv. Algoritmi genetici1.3.4.5. Reele neurale1.3.4.6. Teoria jocurilor1.3.4.7. nvarea automat (Machine learning)1.3.4.8. Ageni inteligeni1.3.4.9. Sisteme expert1.3.4.10. Sisteme fuzzy

1.3.5. Sisteme i maini inteligente1.3.5.1. Deep Blue1.3.5.2. Sisteme de traducere automat1.3.5.3. Optical Character Recognition1.3.5.4. DENDRAL1.3.5.5. Roboi

1.3.6. Computere SPRAY: praf inteligent, vopsea inteligent

313131333436

3942424547515151525253545455565757575858585859


6/190

Ioan Dziac, Inteligen artificial, 2008VI

CAPITOLUL 2. SOFT COMPUTING2.1. Raionament nuanat. Logic fuzzy

2.1.1. Generaliti2.1.2. Logica fuzzy2.1.3. Mulimi crisp. Mulimi fuzzy2.1.4. Submulimi fuzzy

2.1.5. Relaii ntre mulimi fuzzy2.1.6. Numere fuzzy2.1.7. Operaii cu mulimi fuzzy2.1.8. Implicaii pentru logica fuzzy2.1.9. Operatori de compunere fuzzy2.1.10. Fuzificarea i defuzificarea informaiei2.1.11. Evaluarea i aprecierea. Scale liniare i neliniare

2.2. Calcul neural. Reele neurale. Reele neuro-fuzzy2.2.1. Uniti funcionale (de procesare) ale reelelor neurale2.2.2. Arhitectura reelelor neurale2.2.3. Algoritmi de funcionare i nvare a unei reelele neurale

2.2.4. Reele neuro-fuzzy. Un exemplu de aplicaie neuro-fuzzy2.2.4.1. Modelarea neuro-fuzzy2.2.4.2. Utilizarea modelelor neuro-fuzzy la predicia unor

evenimente2.2.4.3. Aplicaie privind predicia intervalelor de timp la

care pot s apar evenimente n cadrul unui sistem energetic2.3. Calcul evolutiv. Algoritmi genetici2.4. Raionament probabilist. Reele bayesiene

2.4.1. Metoda bayesian2.4.2. Abordarea bayesian2.4.3. Limitele metodei bayesiene

2.4.4. Comparaie ntre abordarea bayesian i factorii decertitudine

2.4.5. Reele bayesiene2.5. Teoria nvrii. Machine Learning

2.5.1. Noiuni de teoria nvrii2.5.2. Despre date2.5.3. Despre informaii2.5.4. Despre cunotine2.5.5. Inferena ca proces de cutare i constrngerile care apar

pentru satisfacerea condiiilor2.5.6. Varietatea metodelor de raionare i rolul variabilelor

2.5.7. Metode din ingineria cunoaterii pentru nvareaautomatelor

2.5.8. nvarea inductiv. nvarea prin exemple

616262646971

737380818385869798102104

105107

108109114118118118121122

124126128128131133134

136137

138139


7/190

Ioan Dziac, Inteligen artificial, 2008 VII

2.5.9. Alte metode de nvare ale automatelor2.6.Teoria haosului. Fractali

2.6.1. Despre teoria haosului2.6.2. Fractali

140140140142

CAPITOLUL 3. SISTEME BAZATE PE CUNOTINE.

SISTEME EXPERT3.1. Exemple de sisteme expert3.2. Sisteme expert bazate pe reguli

3.2.1. Despre cunotine3.2.2. Regulile ca i tehnic de reprezentare a cunotinelor3.2.3. Structura unui sistem expert bazat pe reguli3.2.4. Caracteristicile fundamentale ale unui sistem expert3.2.5. Avantajele i dezavantajele unui sistem expert bazat pe

reguli3.2.6. Managementul incertitudinii n sistemele expert bazate

pe reguli

3.3. Sisteme expert fuzzy3.3.1. Generaliti3.3.2. Reguli fuzzy3.3.3. Inferene fuzzy3.3.4. Construirea unui sistem expert fuzzy

3.4. Proiectarea sistemelor expert

155155159159160161164

166

167

169169170172172175

BIBLIOGRAFIE 177


8/190

Ioan Dziac, Inteligen artificial, 2008VIII

LIST DE ABREVIERI

AAAI - American Association for Artificial IntelligenceACM - Association for Computing Machinery

AIAI - Artificial Intelligence Applications InstituteAT&T - Bell LabsAUAI - The Association for Uncertainty in Artificial Intelligence ()CLIPS - C Language Integrated Production SystemEC - Evolutionary ComputationEQ - Inteligena emoionalFL - Fuzzy LogicIA - Inteligen artificialIQ - Intelligence quotientIN Inteligen naturalISI -Instituteof Scientific Information

MIT - AI lab at Massachusetts Institute of TechnologyML - Machine LearningNC - Neural ComputingOCR - Optical Character RecognitionOPS - Official Production SystemPR - Probabilistic ReasoningSC - Soft ComputingSE - Sistem expertTI - Tehnologia Informaiei


9/190

O INTRODUCERE SUMAR N IA

n aceast lucrare INTELIGENA ARTIFICIAL (IA) se va consideraca fiind o imitaie aproximativ a INTELIGENEI NATURALE (IN).

n aceast introducere vom ncerca s descrierem succint problematica icteva aspecte eseniale ale IA n raport cu IN (v. fig.1 i 2).

Figura 1. Inteligena artificial - imitaie aproximativ a inteligenei naturale


10/190

Ioan Dziac, Inteligen artificial, 20082

Figura 2. Problematica IA

1. CE este IA? Testul Turing, cuvinte i sintagme cheie

IA este tiina care i propune s gseasc soluii la probleme complexecare erau apanajul inteligenei umane, cu ajutorul programelor de calculatorsau a mainilor automate.

Dei IA ca tiin, este considerat, n general, ca o ramur a Informaticii,Tehnologiei Informaiei sau a tiinei Calculatoarelor, trebuie s evideniemlegturile sale puternice cu alte tiine, cum ar fi Matematica (Logica, Teoriaprobabilitilor), Psihologia (Inteligena uman, Teoria nvrii), Medicina(Neurotiinele), Gnoseologia (Teoria cunoaterii), Biologia, Filozofia i multe

altele. Abilitatea de a combina cunoaterea din toate aceste domenii duce laprogres n crearea IA.

La nceput, crearea i cercetarea IA s-a desfurat pe terenul psihologiei,punndu-se accent pe inteligena lingvistic, ca de exemplu la testul Turing (v.fig. 3). Acest test const ntr-o conversaie n limbaj uman natural cu o main(computer, program) care a fost programat special pentru acest test. Exist unjuriu uman care converseaz cu acest computer, dar i cu un om, prin cte uncanal pur text (fr ca ei s se vad sau s se aud, dac interlocutor 1 estemaina, atunci interlocutor 2 este omul i invers). n cazul n care juriul nupoate s-i dea seama care este computerul i care omul, atunci inteligenaartificial(programul/calculatorul) a trecut testul. n acest mod, Turing a dat o

definiie implicit a IA, evitnd disputele filozofice i rigorile unei definiiiformale.


11/190

Ioan Dziac, Inteligen artificial, 2008 3

Figura 3. Schema testului Turing

Cuvinte i sintagme cheie n IA: inteligen artificial (artificialintelligence), reele neurale (neural networks), reele semantice (semanticnetworks), reele bayesiene/reele de ncredere (Bayesian networks/beliefnetworks), sisteme bazate pe cunotine (knowledge based systems), sistemeexpert (expert systems), sisteme fuzzy (fuzzy systems), sisteme hibride, calcul

inteligent (intelligent computing), calcul natural (natural computing), calculevolutiv (evolutionary computing), algoritmi genetici (genetic algorithms),calcul sumar (soft computing), calcul emergent (swarm computing), antscomputing (calcul de tip muuroi), calcul membranar (membrane computing),calcul n limbaj natural (natural language computing), agent, multi-agent, robot,colonie de roboi, nvare automat (machine learning), test Turing etc.

Lsm deschis lista unor ntrebri de natur filozofic, unele chiarocante: Exist IA? Este ea necesar? Nu este periculoas pentru omenire?

2. DE CE studiem, cercetm i producem IA?

Figura 4. Coperta Revistei Engineering Applications of Artificial Intelligence 1

1http://www.sciencedirect.com/science/journal/09521976


12/190


Argument. Dintre cele mai cunoscute i utile aplicaii ale IA, care duc laprogres (n tiin, tehnologie, economie i viaa social), putem enumera:

rezolvarea automat a problemelor, demonstrarea automat a teoremelor, traducerea automat a textelor, ageni inteligeni, recunoaterea formelor/tiparelor (pattern recognition),

voce electronic, sisteme expert, robotic, asisten inteligent n sntate, nvare automat (machine lerning) instruire asistat de calculator, marketing i management asistat, telecomunicaii bazate pe computer, internet i aplicaii web,

motoare de cutare, inginerie, proiectare asistat jocurii altele.

3. UNDE se studiaz, cerceteaz i promoveaz IA ?

Programe de licen (ciclul I universitar) n Romnia:IA se studiaz mai nou, de cele mai multe ori ca disciplin obligatorie, n

cadrul a tot mai multe specializri universitare de licen din toate centrele

universitare care au astfel de programe de studii: informatic, informaticeconomic, cibernetic, calculatoare, tehnologia informaiei, automatizri,robotic, energetic,etc.

Master n IA (ciclul II universitar, programe acreditate de ARACISncepnd cu 2008-2009 n Romnia):

1. Universitatea Babe-Bolyai, Cluj- Napoca: Sisteme inteligente;2. Universitatea din Bucureti:Inteligen artificial;3. Universitatea Tehnic Gheorghe Asachi Iai, Sisteme inteligente;4. Universitatea din Craiova: Metode i modele n inteligen

artificial;

5. Universitatea Dunrea de Jos Galai: Sisteme inteligente;6. Universitatea de Vest din Timioara: Inteligen artificial i calculdistribuit (Informatic);Nano-Microsisteme inteligente(Fizic).


13/190


Cercetare n Romnia:1) Institutul de Cercetri pentru Inteligen al Academiei Romne

http://www.racai.ro2) Centrul de Cercetri Cognitive i Neuronale (Coneural, institut privat)

http://www.coneural.org

Forumuri n Romnia:1) http://www.inteligenta-artificiala.ro/2) Clubul de inteligen artificial a Facultii de Informatic din Iai

(Universitatea A.I. Cuza)http://profs.info.uaic.ro/~alaiba/club-ai/index.php?title=Pagina_principal%C4%83

Reviste romneti cotate ISI, care public articole tiinifice din domeniulIA:

1) International Journal of Computers, Communications and Control(apare n Editura Universitii Agora, Oradea din 2006, fondatori IoanDziac (Editor executiv), Florin-Gheorghe Filip- Editor ef i M.-J.Manolescu - Managing editor, cu articole introduse n ISI Web ofScience ncepnd cu Vol.1, numrul suplimentar din 2006),http://www.journal.univagora.ro

2) Romanian Journal of Information Science and Technology (apare nEditura Academiei Romne, Bucureti din 1998, Editor ef - DanDasclu, Editor executiv - Gheorghe Pun, cu articole introduse n ISIWeb of Science ncepnd cu Vol.10, Nr.1/2007),http://www.imt.ro/romjist/

Asociaii i institute internaionale de cercetare remarcabile:1) AAAI: American Association for Artificial Intelligencehttp://www.aaai.org/home.html

2) ACM: the Association for Computing Machineryhttp://www.acm.org/3) AIAI: Artificial Intelligence Applications Institutehttp://www.aiai.ed.ac.uk/4)AT&T Bell Labshttp://www.research.att.com/5) Carnegie Mellon University Artificial Intelligence Repositoryhttp://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/0.html6) MIT: AI lab at Massachusetts Institute of Technologyhttp://www.csail.mit.edu/7) IJCAI Home Page

http://ijcai.org/8) The Association for Uncertainty in Artificial Intelligence (AUAI)http://www.auai.org/


14/190


Mari universiti din lume unde se studiaz IA:1) MIT: Massachusetts Institute of Technology: http://web.mit.edu/2) University of California Berkeley: http://berkeley.edu/3) Stanford University: http://www.stanford.edu/4) Oxford University: http://www.robots.ox.ac.uk/~aisoc/5) University of Edinburgh: http://www.inf.ed.ac.uk/6) Yowa State University:http://www.cs.iastate.edu/~honavar/aigroup.html

Cele mai prestigioase reviste internaionale care public articole tiinificen domeniul IA:

Sursa: http://www.thomsonscientific.com/cgi-bin/jrnlst/jlsubcatg.cgi?PC=D

Data accesrii: 02.12.2008

SCIENCE CITATION INDEX EXPANDED - COMPUTER SCIENCE,ARTIFICIAL INTELLIGENCE - JOURNAL LIST

Total journals: 100

1. ADAPTIVE BEHAVIOR2. ADVANCED ENGINEERING INFORMATICS3. AI COMMUNICATIONS4. AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSISAND MANUFACTURING5. AI MAGAZINE6. ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE7. APPLIED ARTIFICIAL INTELLIGENCE8. APPLIED INTELLIGENCE9. APPLIED SOFT COMPUTING10. ARTIFICIAL INTELLIGENCE

11. ARTIFICIAL INTELLIGENCE IN MEDICINE12. ARTIFICIAL INTELLIGENCE REVIEW13. ARTIFICIAL LIFE14. AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS15. AUTONOMOUS ROBOTS16. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS17. COGNITIVE SYSTEMS RESEARCH18. COMPUTATIONAL INTELLIGENCE19. COMPUTATIONAL LINGUISTICS20. COMPUTER SPEECH AND LANGUAGE21. COMPUTER VISION AND IMAGE UNDERSTANDING22. COMPUTING AND INFORMATICS23. CONNECTION SCIENCE

24. CONSTRAINTS25. DATA & KNOWLEDGE ENGINEERING26. DATA MINING AND KNOWLEDGE DISCOVERY27. DECISION SUPPORT SYSTEMS


15/190


28. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE29. ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING ANDCOMMUNICATIONS30. EVOLUTIONARY COMPUTATION31. EXPERT SYSTEMS32. EXPERT SYSTEMS WITH APPLICATIONS33. GENETIC PROGRAMMING AND EVOLVABLE MACHINES

34. IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE35. IEEE INTELLIGENT SYSTEMS36. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION37. IEEE TRANSACTIONS ON FUZZY SYSTEMS38. IEEE TRANSACTIONS ON IMAGE PROCESSING39. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING40. IEEE TRANSACTIONS ON NEURAL NETWORKS41. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE42. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS43. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS44. IET COMPUTER VISION

45. IMAGE AND VISION COMPUTING46. INFORMATION FUSION47. INFORMATION TECHNOLOGY AND CONTROL48. INTEGRATED COMPUTER-AIDED ENGINEERING49. INTELLIGENT AUTOMATION AND SOFT COMPUTING50. INTELLIGENT DATA ANALYSIS51. INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTERSCIENCE52. INTERNATIONAL JOURNAL OF APPROXIMATE REASONING53. INTERNATIONAL JOURNAL OF COMPUTER VISION54. INTERNATIONAL JOURNAL OF FUZZY SYSTEMS55. INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISIONMAKING56. INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION ANDCONTROL57. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS58. INTERNATIONAL JOURNAL OF NEURAL SYSTEMS59. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIALINTELLIGENCE60. INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGEENGINEERING61. INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS62. INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS63. INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION64. INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS65. JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH

66. JOURNAL OF AUTOMATED REASONING67. JOURNAL OF CHEMOMETRICS68. JOURNAL OF COMPUTER AND SYSTEMS SCIENCES INTERNATIONAL


16/190


69. JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE70. JOURNAL OF HEURISTICS71. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS72. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS73. JOURNAL OF INTELLIGENT INFORMATION SYSTEMS74. JOURNAL OF INTELLIGENT MANUFACTURING75. JOURNAL OF MACHINE LEARNING RESEARCH

76. JOURNAL OF MATHEMATICAL IMAGING AND VISION77. JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING78. JOURNAL OF WEB SEMANTICS79. KNOWLEDGE AND INFORMATION SYSTEMS80. KNOWLEDGE ENGINEERING REVIEW81. KNOWLEDGE-BASED SYSTEMS82. MACHINE LEARNING83. MACHINE VISION AND APPLICATIONS84. MECHATRONICS85. MEDICAL IMAGE ANALYSIS86. MINDS AND MACHINES87. NETWORK-COMPUTATION IN NEURAL SYSTEMS88. NEURAL COMPUTATION

89. NEURAL COMPUTING & APPLICATIONS90. NEURAL NETWORK WORLD91. NEURAL NETWORKS92. NEURAL PROCESSING LETTERS93. NEUROCOMPUTING94. PATTERN ANALYSIS AND APPLICATIONS95. PATTERN RECOGNITION96. PATTERN RECOGNITION LETTERS97. REAL-TIME IMAGING98. ROBOTICS AND AUTONOMOUS SYSTEMS99. SOFT COMPUTING100. TRAITEMENT DU SIGNAL

SCIENCE CITATION INDEX EXPANDED - COMPUTER SCIENCE,CYBERNETICS - JOURNAL LISTTotal journals: 19

1. ACM TRANSACTIONS ON COMPUTER-HUMAN INTERACTION2. BEHAVIOUR & INFORMATION TECHNOLOGY3. BIOLOGICAL CYBERNETICS4. CONTROL AND CYBERNETICS5. CYBERNETICS AND SYSTEMS6. HUMAN-COMPUTER INTERACTION7. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMSAND HUMANS

8. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS9. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS


17/190


10. INTERACTING WITH COMPUTERS11. INTERNATIONAL JOURNAL OF HUMAN-COMPUTER INTERACTION12. INTERNATIONAL JOURNAL OF HUMAN-COMPUTER STUDIES13. JOURNAL OF COMPUTER AND SYSTEMS SCIENCES INTERNATIONAL14. KYBERNETES15. KYBERNETIKA16. MACHINE VISION AND APPLICATIONS

17. MODELING IDENTIFICATION AND CONTROL18. PRESENCE-TELEOPERATORS AND VIRTUAL ENVIRONMENTS19. USER MODELING AND USER-ADAPTED INTERACTION

SCIENCE CITATION INDEX EXPANDED - COMPUTER SCIENCE,THEORY & METHODS - JOURNAL LISTTotal journals: 90 (din acestea am selectat doar 23, care au i profil IA)

1. ACM TRANSACTIONS ON COMPUTATIONAL LOGIC2. ARTIFICIAL LIFE3. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE4. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE5. EVOLUTIONARY COMPUTATION6. EXPERT SYSTEMS

7. FUZZY SETS AND SYSTEMS8. GENETIC PROGRAMMING AND EVOLVABLE MACHINES9. HUMAN-COMPUTER INTERACTION10. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION11. IEEE TRANSACTIONS ON NEURAL NETWORKS12. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-

SYSTEMS AND HUMANS13. IMAGE AND VISION COMPUTING14. INTERNATIONAL JOURNAL OF GENERAL SYSTEMS15. INTERNATIONAL JOURNAL OF QUANTUM INFORMATION16. JOURNAL OF CELLULAR AUTOMATA17. JOURNAL OF LOGIC AND COMPUTATION18. JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING

19. JOURNAL OF SYMBOLIC COMPUTATION20. MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING21. QUANTUM INFORMATION & COMPUTATION22. ROMANIAN JOURNAL OF INFORMATION SCIENCE AND TECHNOLOGY23. THEORY AND PRACTICE OF LOGIC PROGRAMMING

SCIENCE CITATION INDEX EXPANDED - ROBOTICS & AUTOMATICCONTROL - JOURNAL LISTTotal journals: 58

1. ANNUAL REVIEWS IN CONTROL2. ASIAN JOURNAL OF CONTROL3. ASSEMBLY AUTOMATION

4. AT-AUTOMATISIERUNGSTECHNIK5. AUTOMATICA6. AUTOMATION AND REMOTE CONTROL


18/190


7. AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS8. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS9. CONTROL & AUTOMATION10. CONTROL AND CYBERNETICS11. CONTROL ENGINEERING12. CONTROL ENGINEERING PRACTICE13. DISCRETE EVENT DYNAMIC SYSTEMS-THEORY AND APPLICATIONS

14. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE15. ESAIM-CONTROL OPTIMISATION AND CALCULUS OF VARIATIONS16. EUROPEAN JOURNAL OF CONTROL17. IEEE CONTROL SYSTEMS MAGAZINE18. IEEE ROBOTICS & AUTOMATION MAGAZINE19. IEEE TRANSACTIONS ON AUTOMATIC CONTROL20. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING21. IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY22. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS23. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS24. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS25. IEEE-ASME TRANSACTIONS ON MECHATRONICS

26. IET CONTROL THEORY AND APPLICATIONS27. IMA JOURNAL OF MATHEMATICAL CONTROL AND INFORMATION28. INFORMATION TECHNOLOGY AND CONTROL29. INTELLIGENT AUTOMATION AND SOFT COMPUTING30. INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNALPROCESSING31. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY32. INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTERSCIENCE33. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL34. INTERNATIONAL JOURNAL OF CONTROL35. INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS36. INTERNATIONAL JOURNAL OF FUZZY SYSTEMS37. INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION ANDCONTROL38. INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION39. INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL40. INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE41. JOURNAL OF CHEMOMETRICS42. JOURNAL OF DYNAMIC SYSTEMS MEASUREMENT AND CONTROL-TRANSACTIONS OF THE ASME43. JOURNAL OF DYNAMICAL AND CONTROL SYSTEMS44. JOURNAL OF MACHINE LEARNING RESEARCH45. JOURNAL OF PROCESS CONTROL46. JOURNAL OF SYSTEMS ENGINEERING AND ELECTRONICS47. JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIEDMATHEMATICS

48. MATHEMATICS OF CONTROL SIGNALS AND SYSTEMS49. MEASUREMENT & CONTROL50. MECHATRONICS


19/190


51. MODELING IDENTIFICATION AND CONTROL52. OPTIMAL CONTROL APPLICATIONS & METHODS53. PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING54. REVISTA IBEROAMERICANA DE AUTOMATICA E INFORMATICA INDUSTRIAL55. ROBOTICS AND AUTONOMOUS SYSTEMS56. SIAM JOURNAL ON CONTROL AND OPTIMIZATION

57. SYSTEMS & CONTROL LETTERS58. TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL

SCIENCE CITATION INDEX EXPANDED - COMPUTER SCIENCE,INTERDISCIPLINARY APPLICATIONS - JOURNAL LISTTotal journals: 96 (din acestea am selectat doar 28, care au i profil IA)

1) AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGNANALYSIS AND MANUFACTURING

2) APPLIED SOFT COMPUTING3) ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING4) BIOINFORMATICS5) BIOMEDICAL ENGINEERING-APPLICATIONS BASIS COMMUNICATIONS6) COMPUTATIONAL BIOLOGY AND CHEMISTRY7) COMPUTATIONAL GEOSCIENCES8) COMPUTATIONAL LINGUISTICS9) COMPUTATIONAL STATISTICS & DATA ANALYSIS10) COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE11) COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL

ENGINEERING12) IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE13) IEEE TRANSACTIONS ON MEDICAL IMAGING14) IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-

APPLICATIONS AND REVIEWS15) IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND

BIOINFORMATICS

16) INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISIONMAKING

17) INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS18) JOURNAL OF BIOMEDICAL INFORMATICS19) JOURNAL OF COMPUTATIONAL BIOLOGY20) MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING21) MEDICAL IMAGE ANALYSIS22)NEUROINFORMATICS23) QSAR & COMBINATORIAL SCIENCE24) QUEUEING SYSTEMS25) ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING26) SAR AND QSAR IN ENVIRONMENTAL RESEARCH27) SOFT COMPUTING

28) SPEECH COMMUNICATION


20/190


SCIENCE CITATION INDEX EXPANDED - COMPUTER SCIENCE,INFORMATION SYSTEMS - JOURNAL LISTTotal journals: 104 (din acestea am selectat doar 16, care au i profil IA)

1. ACM TRANSACTIONS ON COMPUTER-HUMAN INTERACTION1. DATA & KNOWLEDGE ENGINEERING2. DATA MINING AND KNOWLEDGE DISCOVERY

3. DECISION SUPPORT SYSTEMS4. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE5. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING6. INFORMATION TECHNOLOGY AND CONTROL7. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS &

CONTROL8. INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION

MAKING9. INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS10. INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION

SYSTEMS11. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND

VIDEO TECHNOLOGY

12. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION13. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION14. JOURNAL OF WEB SEMANTICS15. KNOWLEDGE AND INFORMATION SYSTEMS16. MEDICAL INFORMATICS AND THE INTERNET IN MEDICINE

Observaie. Dintr-o list de 584 de reviste de COMPUTER SCIENCE inclusen baza de date ISI de Thomson Reuters, la categoria SCIENCE CITATIONINDEX EXPANDED, un numr de 244 de reviste public articole tiinificedespre IA, avnd denotaia sau conotaia chiar n titlul revistei. n realitatenumrul revistelor care public articole tiinifice despre IA este cu mult maimare. Titlurile revistelor de mai sus dovedesc marea varietate a subdomeniilor

IA i ponderea mare pe care o ocup IA n cercetarea i aplicaiile actuale.

4. CINE? Autori, conductori de doctorate, cercettori

Cri de referin din domeniul IA din Romnia:1) N. ndreanu: -Introducere in programarea logica. Limbajul Prolog,

Editura Intarf, 1994;2) D. Dumitrescu, H.Costin: - Reele neuronale, Teorie i aplicaii, Ed.

Teora, Bucureti,1996;3) H. Luchian: - Clasificare evolutiv, Iasi, 1999;

4) D. Dumitrescu: -Principiile inteligenei artificiale, Ed. Albastr, Cluj-Napoca, 1999;


21/190


5) N. ndreanu: - Sisteme Expert. Reprezentarea cunotintelor iinferena, Editura Universitaria, 2001, 344 p.;

6) R. Andonie, A. Caaron, Inteligen computaional, Editura Univ.Transilvania Braov, 2002;

7) B. E Brbat: - Sisteme inteligente orientate spre agent, Ed. AcademieiRomne, 2002;

8) N. ndreanu: -Baze de cunostine, Editura Sitech, 2004;9) H.-N. Teodorescu, M. Zbancioc, O. Voroneanu, Sisteme bazate pe

cunotinte. Aplicaii,Editura Performantica, Iasi, 2004;10)T.I. Bjenescu, Performantele inteligentei artificiale - de la teorie la

aplicaii(ed. II), Ed. Albastr, 2008;11)L.A. Zadeh, D. Tufi, F. G Filip., I. Dzitac I.(eds.), From Natural

Language to Soft Computing: New Paradigms in Artificial Intelligence ,Editing House of Romanian Academy, 2008.

Rzvan Andonie(UT Braov)

Titu I. Bjenescu(AT Militar)

Boldur E. Brbat(ULB Sibiu)

Dan Dumitrescu(UBB Cluj)

Henri Luchian(UAIC Iai)

Nicolae ndreanu(U Craiova)

Figura 5. Civa dintre cercettori, profesori i autori de cri din domeniul IA dinRomnia


22/190


Doctorate n IA n Romnia:

Aproape n toate centrele universitare mari, unde exist coli doctorale ndomeniul Informatic sau tiina calculatoarelor (i nu numai), se elaboreaz ise susin teze de doctorat pe teme de IA.

De exemplu, exist conductorii de doctorat n IA n urmtoarele centreuniversitare:

1) Bucureti (A. C. Atanasiu, F.G. Filip, V. Mitrana, D. Tufi)2) Braov (R. Andonie)3) Cluj (D. Dumitrescu)4) Craiova (N. ndreanu)5) Iai (D. Cristea, D. Glea, H. Luchian, H. N. Teodorescu),6) Timioara (B. Brbat, V. Negru, S. Preitl).

Cercettori romni importani n IA

Grigore C. Moisil(1906-1973)

Solomon Marcusn. 1935

Paul Dan Cristean. 1941

F.G. Filipn. 1947

Gheorghe Punn. 1950

H.-N. Teodorescun. 1951 Gheorghe Tecuci

n. 1954Dan Tufi

n. 1954

Figura 6. Civa dintre cercettorii romni importani n IA

1. Grigore C. Moisil(1906-1973): Logici cu mai multe valori. Pionier alinformaticii recunoscut de IEEE Computer Society,http://www.ici.ro/romania/ro/stiinta/moisil.html


23/190


2. Solomon Marcus (n. 1935): Lingvistic matematic, Gramatici iautomate finite. Membru al Academiei Romnehttp://www.imar.ro/~smarcus/

3. Paul Dan Cristea, Reele neurale, Informatic medical. MembruCorespondent al Academiei Romne,http://www.dsp.pub.ro/info/staff/pcristea.htm

4. Florin Gheorghe Filip: Sisteme suport pentru decizii cu cunotinecombinate (modele numerice i elemente de inteligen artificial).Membru al Academiei Romne,http://www.ici.ro/ici/homepage/filipf.html

5. Gheorghe Pun(DNA Computing, Membrane computing, P Systems),Cercettor la Instititul de Matematic al Academiei Romne i asociat laUniversitatea din Sevilla. Membru Corespondent al Academiei Romne,Membru al Academiei Europea .http://www.imar.ro/~gpaun/

6. Horia-Nicolai Teodorescu (Fuzzy szstems, Artificial live), MembruCorespondent al Academiei Romne, profesor la Universitatea TehnicGheorghe Asachi din Iai http://www.fict.ro/HNT.htm

7. Gheorghe Tecuci (Instructable agents, multistrategy learning, mixed -initiative reasoning, modeling and knowledge acquisition, ontologies,knowledge engineering), Membru al Academiei Romne, profesor laGeorge Mason University, SUA,http://lalab.gmu.edu/members/tecuci.htm

8. Dan Tufi (Corpus Linguistics, Intelligent Computer Aided LanguageLearning, Machine Language Learning, Machine Translation, NaturalLanguage Understanding, Natural Language Generation, KnowledgeRepresentation.). Membru Corespondent al Academiei Romne, directorla Istititutului de Cercetri n Inteligen Artificial al AcademieiRomne. http://www.racai.ro/~tufis/

Cele mai populare cri de iniiere n IA pe plan mondial:1) Stuart Russel, Peter Norvig, Artificial Intelligence: A ModernApproach (2nd Edition), Prentice Hall Series in Artificial Intelligence,Hardcover, p. 1112, 2003.2) Michael Negnevitsky, Artificial Intelligence, A Guide to IntelligentSystems, Second Edition, Pearson Education Limited, 2002.3) Toshinori Munakata, Fundamentals of the New Artificial Intelligence,Second Edition, Springer-Verlag London Limited, 20084) Ben Goertzel, Cassio Pennachin, Artificial General Intelligence,

Springer-Verlag Berlin Heidelberg, 2007.


24/190


Fondatori i cercettori pe plan internaional n IA:

George Boole(1815-1864)

Alan Turing(192-1954)

John McCarthyn. 1927

Marvin Minskyn.1927

Lotfi A. Zadehn. 1921

Allen Newell(1937-1992)

Herbert Simon(1916-2001)

Seymour Papertn. 1928

Ray Kurzweiln.1948

Kevin Warwickn.1954.

Figura 7. Civa dintre fondatorii de subdomenii i cercettori n IA pe plan internaional

Ali cercettori n IA (redm textul n limba englez, n original, cf. sursei2)

Cognitive Scientists Ballard, Dana H. - "Animate vision". Computational theories of the

brain with emphasis on human vision. (Univ. of Rochester, USA) Barsalou, Lawrence W. - Perceptual bases of cognition, situated

conceptualization, dynamic representations of concepts, frames,category learning, event memory. Brooks, Rodney A. - Embodied cognition in autonomous robots. (MIT,

USA). Calvin, William H. - Theoretical neurophysiologist and popularizer.

Author of "The Cerebral Code," "How Brains Think," "Conversationswith Neil's Brain" and "A Brain for All Seasons," amongst other works.

Cave, Kyle R. - Cognitive psychology of visual cognition, includingattention, imagery, and object recognition.

Coneural Center for Cognitive and Neural Studies - Research centerfor computational embodied neuroscience. Director: Razvan Florian.

2 http://www.dmoz.org/Computers/Artificial_Intelligence/ (02.12.2008): De menionatc n lista de mai jos mai sunt menionate numele a trei cercettori romni: Rzvan Florian,Rzvan Andonie i Raul Murean.


25/190


Cotterill, Rodney M.J. - Neurophysiology of consciousness, consideredas an active process. Implications of this view for understanding autism.(Danish Technical University, Denmark)

Cziko, Gary- Educational psychology. Darwinian approaches. (Univ. ofIllinois, USA)

Dunbar, Kevin - Scientific discovery and reasoning (especially inmolecular biology); visual, causal, abductive, and analogical reasoning;gender differences in reasoning; science education; mental models;invivo cognition; visualization. (Dartmouth College.)

Gregory, Richard - Influential researcher on perception and perceptualillusion. Site gives access to selected publications as well as his CV andanimated demonstrations of significant illusions.

Jrvilehto, Timo - Finnish Psychologist with interests inpsychophysiology, preception, education, and "the theory of theorganism-environment system".

Kirsh, David - Representation in everyday activity, cognitive

complexity. Koch, Christoph- Neuroscience and consciousness. Kosslyn, Stephen M. - Mental imagery, perception. Kubovy, Michael - Perceptual grouping. Loftus, Elizabeth F. - Psychology of memory, false memory, eyewitness

testimony. Minsky, Marvin - One of the pioneers and most creative thinkers of

Artificial Intelligence research. Modestino, Ed - A graduate student in the Complex Systems and Brain

Sciences program at Florida Atlantic University, working onneuroimaging of complex systems and neural networks of cognition.

Moravec, Hans - Mobile robots and their psychology. Norman, Don - Author of The Design of Everyday Things, list of books

and articles in human-centered design. O'Regan, J. Kevin - Visual perception: "change blindness" (nice

animated demos), active perception, eye movements, consciousness, and"the world as external memory".

Pylyshyn, Zenon W. - Visual attention and preattention, critique of"pictorial" theories of mental imagery, foundational issues in thecomputational theory of the architecture of cognition.

Scaruffi, Piero - Information about Scaruffi's research and teachingactivities in Cognitive Science, Psychology of Consciousness and

Philosophy of Mind, and links to his papers, and to his annotatedbibliography of cognitive science, artificial intelligence, neurobiology,


26/190


artificial life, linguistics, neural networks, connectionism, cognitivepsychology, and consciousness.

Smolensky, Paul- A leading researcher in connectionism. Thomas, Nigel - The philosophical, scientific, and historical study of

imagination and mental imagery, and their role in consciousness andcognition [Cal State LA].

Turner, Mark - Professor and Dean of Arts and Sciences at CaseWestern Reserve University. Research focus is to study how humanthought processes are different than other species with an emphasis onblending.

van Diepen, Paul - Scene perception, eye movements, chronometry ofinformation processing (no longer active in cognitive research).

Zhang, Jiajie - External representations; human-computer interaction;human factors; medical informatics

Fuzzy Intelligence People Abonyi, Janos - Fuzzy modeling for system identification and data

mining De Baets, Bernard- Fuzzy Relations and Preference Modelling Fodor, Jnos - Basics of fuzzy sets and connectives Fortemps, Philippe - Preference modelling Klement, Peter- Triangular Norms Mencar, Corrado - Neuro-fuzzy classifiers Roubens, Marc - Multicriteria decision aid Yager, Ronald R. - Decision support Zadeh, Lotfi A. - inventor of Fuzzy Sets Zimmermann, Hans-Jurgen - Fuzzy O.R.

Neural Networks People

Adelson, Edward T. - Visual perception, machine vision, imageprocessing.

Agakov, Felix - Probabilistic graphical modeling, statistical learningtheory, pattern recognition, prediction, and causality.

Allan, Moray - Computer vision, probabilistic models for imagesequences, invariant features.

Amari, Shun-ichi- Neural network learning, information geometry. Andonie, Razvan - Data structures for computational intelligence. Andrieu, Christophe - Particle filtering and Monte Carlo Markov Chain

methods.

Anthony, Martin - Computational learning theory, discrete mathematics. Attias, Hagai- Graphical models, variational Bayes, independent factor

analysis.


27/190


Bach, Francis - Machine learning, kernel methods, kernel independentcomponent analysis and graphical models

Ballard, Dana H. - Visual perception with neural networks. Bartlett, Marian Stewart - Image analysis with unsupervised learning,

face recognition, facial expression analysis. Beal, Matthew J. - Bayesian inference, variational methods, graphicalmodels, nonparametric Bayes.

Becker, Sue - Neural network models of learning and memory,computational neuroscience, unsupervised learning in perceptualsystems.

Bengio, Samy - Torch machine learning library, including SVMTorchsupport vector machine program. Research on mixture models, hiddenmarkov models, multimodal fusion, speaker verification.

Beveridge, Ross - Computer vision, model-based object recognition,face recognition.

Bishop, Chris - Graphical models, variational methods, pattern

recognition. Boutilier, Craig - Decision making and planning under uncertainty,reinforcement learning, game theory and economic models.

Brody, Carlos D. - Somatosensory working memory, computation withaction potentials, design of complex stimuli for sensoryneurophysiology.

Brown, Andrew - Machine learning of dynamic data, graphical modelsand Bayesian networks, neural networks.

Bulsari, A. - Neural networks and nonlinear modelling for processengineering.

Calvin, William H. - Theoretical neurophysiologist and author of The

Cerebral Code, How Brains Think. Caruana, Rich- Multitask learning. Cheung, Vincent - Machine learning and probabilistic graphical models

for computer vision and computational molecular biology. Chu, Selina - Artificial intelligence, machine learning, data mining. Coolen, Ton - Physics of disordered systems. Working on dynamic

replica theory for recurrent neural networks. Cottrell, Garrison W. - An artrificial intelligence researcher who is an

expert on neural networks. Dahlem, Markus A. - Neural network models of visual cortex to model

neurological symptoms of migraine.

Dayan , Peter - Representation and learning in neural processingsystems, unsupervised learning, reinforcement learning.


28/190


de Freitas, Nando - Bayesian inference, Markov chain Monte Carlosimulation, machine learning.

de Garis, Hugo - Evolvable neural network models, neural networks forprogrammable hardware, large neural networks.

De vito, Saverio - Neural networks for sensor fusion, wireless sensornetworks, software modeling, multimedia assets managementarchitectures

De Wilde, Philippe - Brain inspired models of uncertainty, linguistic andfuzzy uncertainty, uncertainty in dynamic multi-user environments.

Dietterich, Thomas G. - Reinforcement learning, machine learning,supervised learning.

Dr Hooman Shadnia- Dedicated to artificial neural networks and theirapplications in medical research and computational chemistry. Offers aquick tutorial on theory on ANNs written in Persian.

Freeman, William T. - Bayesian perception, computer vision, imageprocessing.

Frey, Brendan J. - Iterative decoding, unsupervised learning Friedman, Nir - Learning of probabilistic models, applications tocomputational biology.

Frohlich, Jochen - Overview of neural networks, and explanation ofJava classes that implement backpropagation, and Kohonen featuremaps.

Garcia, Christophe - Computer vision, image analysis, neural networks. Ghahramani, Zoubin - Sensorimotor control, unsupervised learning,

probabilistic machine learning. Hansen, Lars Kai - Neural network ensembles, adaptive systems and

applications in neuroinformatics.

Herbrich, Ralph - Statistical learning theory, support vector machinesand kernel methods.

Heskes, Tom - Learning and generalization in neural networks. Hinton, Geoffrey E. - Unsupervised learning with rich sensory input.

Most noted for being a co-inventor of back-propagation. Honavar, Vasant - Constructive learning, computational learning theory,

spatial learning, cognitive modelling, incremental learning. Hughes, Nicholas- Automated Analysis of ECG. Jaakkola, Tommi S. - Graphical models, variational methods, kernel m. Jensen, Finn Verner- Graphical models, belief propagation. Jordan, Michael I. - Graphical models, variational methods, machine

learning, reasoning under uncertainty. Joshi, Prashant - Computational motor control, biologically realistic

circuits, humanoid robots, spiking neurons.


29/190


Kearns, Michael - Reinforcement learning, probabilistic reasoning,machine learning, spoken dialogue systems.

Koller, Daphne- Probabilistic models for complex uncertain domains. Lafferty, John D. - Statistical machine learning, text and natural

language processing, information retrieval, information theory. Lawrence, Neil- Probabilistic models, variational methods. Lawrence, Steve - Information dissemination and retrieval, machine

learning and neural networks. LeCun, Yann - Handwritten recognition, convolutional networks, image

compression. Noted for LeNet. Leen, Todd - Online learning, machine learning, learning dynamics. Leow, Wee Kheng - Computer vision, computational olfaction. Lerner, Uri N. - Hybrid and Bayesian networks. Li, Zhaoping - Non-linear neural dynamics, visual segmentation,

sensory processing. Maass, Wolfgang- Theory of computation, computation in spiking

neurons. MacKay, David- Bayesian theory and inference, error-correcting codes,

machine learning. Malchiodi, Dario - Machine learning, Learning from uncertain data. McCallum, Andrew - Machine learning, text and information retrieval

and extraction, reinforcement learning. Meila, Marina - Graphical models, learning in high dimensions, tree

networks. Minka, Thomas P. - Machine learning, computer vision, Bayesian

methods. Muresan, Raul C. - Neural Networks, Spiking Neural Nets, Retinotopic

Visual Architectures. Murphy, Kevin P. - Graphical models, machine learning, reinforcement

learning. Murray, Alan - Neural networks and VLSI hardware. Murray-Smith, Roderick - Gesture recognition, Gaussian Process priors,

control systems, probabilistic intelligent interfaces. Neal, Radford - Bayesian inference, Markov chain Monte Carlo

methods, evaluation of learning methods, data compression. Oja, Erkki - Unsupervised learning, PCA, ICA, SOM, statistical pattern

recognition, image and signal analysis.

Olier, Ivan - Artificial intelligence, generative topographic map, missingdata.


30/190


Olshausen, Bruno - Visual coding, statistics of images, independentcomponents analysis.

Opper, Manfred - Statistical physics, information theory and appliedprobability and applications to machine learning and complex systems.

Paccanaro, Alberto - Learning distributed representation of conceptsfrom relational data.

Pearlmutter, Barak - Neural networks, machine learning, acoustic sourceseparation and localisation, independent component analysis, brainimaging.

Prashant, Joshi - Computational neuroscientist, with main areas ofresearch interest being computational motor control, computationalmodels of olfaction, computation with spiking neurons,neurocomputational basis of working memory and decision making,learning in biologically realistic circuits.

Rao, Rajesh P. N. - Models of human and computer vision. Rasmussen, Carl Edward - Gaussian processes, non-linear Bayesian

inference, evaluation and comparison of network models. Revow, Michael - Hand-written character recognition. Roberts, Stephen - Machine learning and medical data analysis,

independent component analysis and information theory. Rovetta, Stefano - Research on Machine Learning/Neural

Networks/Clustering. Applications to DNA microarray dataanalysis/industrial automation/information retrieval. Teaching activities.

Roweis, Sam T. - Speech processing, auditory scene analysis, machine l. Russell, Stuart - Many aspects of probabilistic modelling, identity

uncertainty, expressive probability models. Rutkowski, Leszek - Neural networks, fuzzy systems, computational int.

Saad, David - Neural computing, error-correcting codes andcryptography using statistical and statistical mechanics techniques.

Sahani, Maneesh - Statistical analysis of neural data, experimentaldesign in neuroscience.

Sallans, Brian - Decision making under uncertainty, reinforcementlearning, unsupervised learning.

Saul, Lawrence K. - Machine learning, pattern recognition, neuralnetworks, voice processing, auditory computation.

Saund, Eric - Intermediate level structure in vision. Schein, Andrew I. - Machine learning approaches to data mining

focussing on text mining applications.

Sejnowski, Terry - Sensory representation in visual cortex, memoryrepresentation and adaptive organization of visuo-motortransformations.


31/190


Seung, Sebastian - Short-term memory, learning and memory in thebrain, computational learning theory.

Shkolnik, Alexander - Neurally controlled robotics. Shuurmans, Dale - Computational learning, complex probability

modelling. Simard, Patrice- Machine learning and generalization. Smola, Alex J. - Kernel methods for prediction and data analysis.

Storkey, Amos - Belief networks, dynamic trees, image models, imageprocessing, probabilistic methods in astronomy, scientific data mining,Gaussian processes and Hopfield neural networks.

Sutton, Richard S. - Reinforcement learning. Sykacek, Peter - Brain Computer Interface. Teh, Yee Whye - Learning and inference in complex probabilistic

models. Tipping, Mike - Varied machine learning and data analysis topics,

including Bayesian inference, relevance vector machine, probabilistic

principal component analysis and visualisation methods. Tishby, Naftali - Machine learning; applications to human-computerinteraction, vision,neurophysiology, biology and cognitive science.

Versace, Massimiliano - Neural networks applied to visual perceptionand computational modeling of mental disorders.

Wainwright, Martin - Statistical signal and image processing, naturalimage modelling, graphical models.

Wallis, Guy - Object recognition, cognitive neuroscience, interactionbetween vision and motor movements.

Weiss, Yair - Vision, Bayesian methods, neural computation. Welling, Max - Unsupervised learning, probabilistic density estimation,

machine vision. Wiegerinck, Wim - Inference in graphical models, mean field and

variational approaches. Williams, Christopher K. I. - Gaussian processes, image interpretation,

graphical models, pattern recognition. Winther, Ole - Variational algorithms for Gaussian processes, neural

networks and support vector machines. Also work on belief propagationand protein structure prediction.

Wiskott, Laurenz - Face recognition, Invariances in learning and vision. Wu, Yingnian - Stochastic generative models for complex visual

phenomena. Xing, Eric - Statistical learning, machine learning approaches to

computational biology, pattern recognition and control.


32/190


Yedidia, Jonathan S. - Statistical methods for inference and learning. Zemel, Richard - Unsupervised learning, machine learning,

computational models of neural processing. Zhou, Zhi-Hua - Neural computing, data mining, evolutionary

computing, ensemble networks.Computers: Robotics: History: People

Asimov, Isaac - Asimov was one of the three grand masters of sciencefiction and the creator of the term "robotics". He is known in the fieldfor his Four Laws of Robotics and the large body of fiction he wroteabout robots. He envisioned a future in which robots were (usually)safe, well-controlled servants of man.

Brooks, Rodney A. - Director of the MIT CS and AI Lab. CTO ofiRobot. Involved in a wide range of robotics research initiatives. Bestknown as the creator of Subsumption Architecture in which layers ofsimple behaviors create complex emergent behaviors.

Capek, Karel - Czech author and playwright who popularized the term

robot in his 1920 play, RUR: Rossum's Universal Robots. Moravec, Hans P. - Researcher at the CMU Robotics Institute whobelieves intelligent machines will be the descendants of the human race.Author of several books on the nature of evolving robot intelligence.Current work involves 3D mapping and stereoscopic vision.

Tesla, Nikola - Tesla demonstrated a robotic boat that he called ateleautomaton in 1898 that many consider to be the first robot.

Tesla's Race of Robots - A summary of Nikola Tesla's work in roboticsdone as part of a PBS documentary on his life. Includes information onhis teleautomaton and his predication of mechanical, automated men.

Tilden, Mark - Creator of BEAM robotics, a controversial philosophy of

robot building that advocates the use of "nervous nets" instead ofconventional microprocessors as controllers, the use of recycled parts,and solar power.

Walter, W. Grey, Online Archive - Biography of one of the pioneers ofrobotics. Includes historical information and photos of many of therobots Walter created in the 1940s and 1950s.

Walter, W. Grey, Robotics Pioneer - A respected neurophysiologist whodid early work on autonomous mobile robots in the 1940s.

Wiener, Norbert - Generally known as the "father of cyborgs". Wienerwas the originator of the term cybernetics and part of a group ofscientists who originated the field. He was also an MIT mathematician,

science fiction author, and designer of an early chess-playing robot.


33/190



34/190


5. CUM? Metode, modele, mijloace, tehnologii

INFORMATIC TEHNOLOGIAINFORMAIEI

TIINACALCULA-TOARELOR

AUTOMA-TIC

CIBERNETIC

ELECTRONIC

NEUROTINELENeuropsihologia

NeurologiaNeuropsihiatriaNeurobiologia

INTELIGENARTIFICIAL

(IA)

MATEMATIC

LogicProbabilitiGrafuri

Limbaje formaleCombinatoric...

BIOLOGIATeoria evoluiei

Teoria emergenei...

PSIHOLOGIA FILOZOFIAGNOSEOLOGIA ...

Figura 8. Principalele tiine implicate n IA

Nu exist o definiie unanim acceptat pentru IA nici ca domeniu

tiinific. Foarte muli consider IA ca un subdomeniu al tiineicalculatoarelor, dar ea studiaz i este strns legat i ar putea fi revendicat casubdomeniu i de Informatic, Tehnologia informaiei, Automatic iCibernetic.

Cert este c IA este un domeniul tiinific interdisciplinar care implic pelng tiinele amintite (cele scrise cu alb n figura 8) i alte tiine (cele scrisecu negru n figura 8), cum ar fi: Psihologia, Biologia, Neurotiinele,Electronica, Matematica, Filozofia etc.

TIPURI DEPROBLEME

MODELARE REZOLVARE ASOCIEREA NTREDATELE DE INTRARE(ipoteze, valori iniiale) IRSPUNSUL CORECT

(concluzie, rezultat)1. Problemebine-puse(date certe, valoriexacte)

Exist unmodel formalal problemei

determinist:HARDCOMPUTING

Relaie funcional explicit

2. Problemeru-puse(date incerte,valoriaproximative,adevr parial)

Nu exist unmodel formal(rspunsuridoar ncazuriparticulare)

aproximativ:SOFTCOMPUTING

nvare (pe baz de exemple deasociere ntrebare-rspuns)

Figura 9. Modelare i metode n IA


35/190


Calculinteligent

(pur simbolic)

Logicafuzzy

Reele neuraleRaionamentprobabilist

Learning Machine

Calculevolutiv

Algoritmigenetici

Calculconvenional

(pur numeric)

HARD

COMPUTING

SOFT COMPUTING

tolerant la imprecizie, nesiguran,adevr parial i aproximare

HARD

COMPUTING

Figura 10. Tipuri de calcul inteligent

Bazndu-ne doar pe logica cu dou valori de adevr (numit itradiional, clasic, binar, boolean, aristotelic), putem rezolva doarPROBLEMELE BINE PUSE, cu date certe, precise, exacte. Dar n practic nentlnim la tot pasul cu probleme care conin noiuni inexacte, n care intervindate incerte, mrimi imprecise, variabile lingvistice sau adevruri pariale,numite i PROBLEME RU-PUSE, probleme care nu pot fi rezolvate princalculul tradiional. Rezolvarea unor astfel de probleme se face azi prin soft

computing, care are la baz logica fuzzy i cteva instrumente ale IA.Logica fuzzy (Fuzzy Logic, Zadeh3, 1973) este o logic nuanat, non-

aristotelic, cu mai mult de dou valori de adevr. Logica fuzzy mpreun cuRaionamentul probabilist (Probabilistic Reasoning), prin utilizarea Calculuievolutiv (Algoritmilor Genetici4) pe Reelele neurale5 i Learning Machine,formeaz un nou stil de calcul, numit SOFT COMPUTING6, cu ajutorul cruiaputem rezolva probleme ru-puse.

Soft Computing-ul, la care se adaug, n mod nedisjunctiv, Sistemeleexpert (din economie, comer, medicin, nvmnt etc.), Sistemele bazate pecunotine, Roboii, Reele semantice, Reelele de ncredere .a., sunt cteva dinsubdomeniile importante ale Inteligenei Artificiale (v. i fig. 11).

3http://www.cs.berkeley.edu/~zadeh/4 n 1975 John Holland, inspirat de teoria evoluiei a lui Darwin, a pus bazele ALGORITMILORGENETICI moderni. Dar exist contribuii premergtoare n domeniu ale unor biologi sau informaticieni:Barriceli (1954), Bremermann (1960), Fraser i Burnell (1970), Crosby )1973) .a. De multe ori algoritmiigenetici se bazeaz pe modele de tip SWARM INTELLIGENCE, de inspirate din inteligena naturalemergent a unor grupuri de insecte, cum ar fi cea a COLONIILOR DE FURNICI.5Prin anii 40, Warren McCulloch i Walter Pitts, inspirai de teoria nvrii condiionate a lui Pavlov, au

pus bazele REELELOR NEURONALE, capabile s nvee pe baza anumitor reguli simple. Ulterior auadus contibuii Hebb (spresftul anilor40, Rosenblat (PERCEPTRON, 1950), Minsky i Papert(PERCEPTRONI, 1969) .a.6 ...the principal constituents of Soft Computing (SC) are Fuzzy Logic (FL), Neural Computing (NC),Evolutionary Computation (EC) Machine Learning (ML) and Probabilistic Reasoning (PR),http://www.soft-computing.de/def.html


36/190


Clase Subclase Modele de calculimitate

Realizri

Calcul neural Reelele bioelectrice dincreierul uman formate deneuroni i sinapseleacestora.

Reele neurale

Calcul evolutiv Principiile darwiniste deevoluie

Algoritmi geneticiCutare armonic

Calcul molecular(DNA Computing)

ADN

Calcul membranar(Membrane Computing)

Membrana celulei

Calcul cuantic(Quantum Computing)

Sistem fizic

Calculnatural

Calcul de tip swarm(Swarm computing)

Colonii de furniciBancuri de petiColonii de bacteriiGrupuri de animaleStoluri de psri

Algoritmi deoptimizare

Calculfuzzy

Control fuzzyReele neuro-fuzzy

Raionamentul umancomun

Sisteme fuzzySisteme neuro-fuzzySisteme expertSisteme hibride

Figura 11. Domeniile i subdomeniile calcului inteligent

Ageni inteligeni

Citm din Boldur Brbat, Sisteme inteligente orientate spreagent [Br02]:

- Ceva software care tie s fac lucruri pe care ai fi putut probabil s lefaci singur, dac ai fi avut timp (Selker, citat de Hermans, 1996).

- Un obiect care gndete (Gentia Software, 1997).- O entitate cu scopuri, aciuni i cunotine ntr-un anumit domeniu, situat

ntr-un mediu (Stone i Veloso, 1997).- O component de software i/sau echipament capabil s acioneze

exigent n scopul ndeplinirii unor sarcini pentru utilizator (Nwana, 1996).(Nwana adaug c prefer s-l foloseasc drept metatermen pentru o gam detipuri de ageni.)

n fine, iat rezumatul unei definiii de sintez, dat de Tecuci (1998), carecuprinde multe din aspectele de mai sus. Un agent inteligent este un sistembazat pe cunotine care: i percepe mediul; raioneaz pentru a interpreta

percepiile, infer, rezolv probleme i stabilete aciuni; acioneaz asupramediului pentru a ndeplini o seam de scopuri sau sarcini pentru care a fostproiectat. [...]


37/190


Ce pretindem de la cineva pe care ni-l alegem ca agent? n esen, treitrsturi (Pallmann, 1999):

a) Competen(inteligen nsoit de cunotine n domeniu).b)Personalizare (chiar dac nu aparine persoanei al crei agent este,

trebuie s presteze serviciile cerute de acest client n stil croit pe msur, nustandard).

c) Reprezentare (s acioneze nu numai pentru, ci i n numele persoaneicare l-a ales, evident, n limitele mputernicirii date).

n fine, adoptnd o perspectiv i mai vdit antropocentric, trstura defrunte a agentului ar putea fi credibilitatea. Aceasta are, ca i n cazuloamenilor, dou subdimensiuni:

a) calitatea de a fi demn de ncredere(trustwortiness);b) competena(expertise).

Limbaje de programare utilizate n IA

LISP. Denumirea LISP vine de la LISt Processing7. Printele su esteJohn McCarthy de la MIT AI Lab, iar anul naterii este considerat anul 1958.LISP este un limbaj declarativ (nu este imperativ). Conceput iniial ca unformalism matematic menit s conduc la dezvoltarea unei teorii riguroase aprogramelor, astzi LISP-ul este un limbaj puternic, n jurul cruia s-a dezvoltatun veritabil mediu de programare. Se poate spune ca LISP-ul este limbajul carear permite s vedem calculatorul nu doar ca pe o complicat main de efectuatcalcule aritmetice, ci ca pe un adevrat creier electronic aflat ntr-o continui exploziv evoluie spre inteligen.

PROLOG. Limbajul Prolog ( PROgrammation en LOGique) a fost creat

la Marsilia la nceputul anilor 70, inventatorii fiind Alain Colmeraurer iPhilippe Roussel.Una din principalele idei ale programrii logice este aceea cun algoritm este constituit din doua elemente disjuncte: logic i control.Componenta logic corespunde definiiei problemei ce trebuie soluionat, ntimp ce componenta control stabilete cum poate fi obinut soluia. Unprogramator trebuie sa descrie numai componenta logic a unui algoritm, lsndcontrolul executrii s fie exercitat de sistemul de programare logic utilizat. Cualte cuvinte, sarcina programatorului este specificarea problemei ce trebuiesoluionat. Astfel, limbajul logic poate fi conceput simultan ca limbaj dedescriere, specificare formal a problemei i ca un limbaj de programare acalculatoarelor.

7http://en.wikipedia.org/wiki/Lisp_programming_language


38/190


Fundamentele teoretice se gsesc n metoda demonstrrii automatedezvoltat ncepnd cu 1965 dup metoda rezoluiei data de Julian Robinson.Un rol important l-a avut si Robert Kowalski8prin demonstrarea faptului ca sepoate programa folosind logica. n limbajul Prolog9se poate face orice ca i nalte limbaje de programare. ns Prologul are avantaje distincte, precum idezavantaje. Prelucrarea rapida a datelor numerice este un punct vulnerabil allui. Prologul poate mnui numere, ns nu aa de eficient ca un limbaj specialdestinat acestui lucru. Prologul, nsa, puncteaz cnd e vorba de manipulareasimbolurilor. Ori manipularea simbolurilor este inima a ceea ce a devenit azicunoscut sub numele de IA.

CLIPS este un acronim pentru C Language Integrated ProductionSystem, un sistem expert dezvoltat de NASA n anii 1980. Sintaxa i numele aufost inspirate de OPS (sistem de producie oficial, n englez OfficialProduction System) creat de Charles Forgy. Primele versiuni de CLIPS au fostdezvoltate ncepnd cu 1984 la NASA -Johnson Space Center (ca o alternativla sistemul existent numit ART*Inference) pn la nceputul anilor 1990 cnd

subvenia a ncetat din cauza problemelor bugetului Federal i a unui ordinconform cruia NASA trebuia s cumpere software comercial n loc s-ldezvolte.

CLIPS este probabil cel mai folosit sistem expert, deoarece este rapid,eficient i gratuit. Cu toate c acum face parte din domeniul public, este ncactualizat i susinut de autorul original, Gary Riley10.

CLIPS ncorporeaz un limbaj de programare orientat obiect numit COOLpentru a scrie sisteme expert. Cu toate c este scris n limbajul de programare C,interfaa sa seamn foarte mult cu cea a limbajului de programare LISP. Se potscrie extensii n C, iar CLIPS poate fi chemat din C.Ca i alte sisteme expert, CLIPS are de-a face cu reguli i fapte. n timpul rulrii

programelor, existena diferitelor fapte ntr-o baz de cunotine pot face ca oregul s fie aplicabil.

8http://www.doc.ic.ac.uk/~rak/9http://thor.info.uaic.ro/~georgie/prolog/introducere.html10http://clipsrules.sourceforge.net/


39/190


CAPITOLUL 1

INTELIGENA ARTIFICIAL CA IMITAIEAPROXIMATIV A INTELIGENEI NATURALE

Rezumat. Paradoxul aproximrii inteligenei naturale prin inteligenaartificial: Ceea ce omul face mai uor (de exemplu: recunoatere vizual,vorbire, mers, nvare) e mai greu de imitat prin inteligen artificial;iar ceea ce omul face mai greu (de exemplu: calcule matematice, calculesimbolice, memorare) e mai uor de imitat prin inteligen artificial.Cel mai bune rezultate se obin imitnd inteligena emergent a grupurilorde animale sociale.

1.1. Inteligena natural uman

1.1.1. Generaliti

ntr-o descriere aproximativ, inteligena uman ar fi capacitateaindividului de a nva uor i bine, uurina de a soluiona probleme noi, de ase adapta la situaii noi, pe baza experienei acumulate.

William Stern a descris inteligena uman ([Ste12], [Ste38]), ca fiindaptitudinea general a individului de a-i adapta contient gndirea unorcerine noi: ea este capacitatea spiritual de adaptare general la noile cerine

i condiii ale vieii.n latin, intelligere nseamn a relaiona, a organiza, iar interlegerensemna stabilirea de relaii ntre oameni. Probabil c aceste dou cuvinte au olegtur strns cu etimologia cuvntului inteligen. Cuvntul inteligentprovine tot din limba latin de la intelligo, care n traducere nseamn detept,nelept, priceput, ager la minte. Pe scurt, inteligena ar putea fi definit ca fiindcapacitatea minii de a stabili legturi ntre diferite date.

n [DEX98] gsim descrierea: INTELIGN, inteligene, s.f.Capacitatea de a nelege uor i bine, de a sesiza ceea ce este esenial, de arezolva situaii sau probleme noi pe baza experienei acumulate anterior;deteptciune [...].

Inteligena umaneste obiectul de studiu al psihologiei n colaborare cuneurotiinele (neurofiziologia, neuropsihologia, neuroanatomia, etc),psihofizica, psihologia comportamental, cibernetica biologic, biomecanica,


40/190


inteligena artificial, teoria controlului, management, informatica imatematicile aplicate, respectiv robotica, mecatronica i controlul automat.

Pentru msurarea inteligenei este vehiculat termenul de coeficient deinteligensau IQ (intelligence quotient), care este un scor derivat din unul saumai multe teste psihometrice standardizate de msurare a inteligenei.

Definirea noiunii de inteligen uman (delimitarea i clarificareaaspectelor sale cantitative i calitative) sunt probleme extrem de dificile i eleau fost abordate de muli oameni de tiin, n special, psihologi, dintre care seremarc:

Alfred Binet(18571911) - psiholog i psihometrician francez, autor alcelebrului test de inteligen utilizat pentru msurarea inteligeneicognitive(IQ);

Thodore Simon (1872 - 1961) psiholog i psihometrician francez,care a contribuit la stabilirea faimoasei scale de inteligen, cunoscutsub numele de scala de inteligen Binet- Simon;

William Lewis Stern (1871-1938) - psiholog german, inventatorulcoeficientului de inteligenpe baza cruia se face testul IQ;

Lewis Madison Terman (1877-1946) psiholog american, pionier alpsihologiei cognitive, profesor la Universitatea Stanford, care a pus lapunct, pe baza lucrrilor lui Binet, testul de inteligen cunoscut subnumele de testul IQ Stanford-Binet;

Edouard Claparde (1873-1940) - neurolog i psiholog elveian, cares-a ocupat de studiulpsihologiei copilului i a tipurilor de memorie;

Jean Piaget (1896-1980) - filozof i om de tiin elveian care s-aocupat de studiul etapelor dezvoltrii cognitive. Piaget a spus despreinteligen c este ceea ce foloseti cnd nu tii ce s faci i cinteligena nseamn a nelege i a inventa ;

Howard Gardner(n. 1943) - fondatorul teoriei inteligenelor multiple; Daniel Goleman (n. 1946) - psiholog american care s-a ocupat de

studiul inteligenei emoionale(EQ); i alii: cele mai recente studii legate de inteligena emoional se

datoreaz lui Steven J. Stein, Howard E. Booki Karl Albrecht.

Secolul XX a fost dominat de conceptul IQ, ca indicator extrem deimportant n anticiparea performanelor de care ar fi putut fi capabil un individ,despre care se spune c nu prea mai poate fi mbuntit pe parcursul vieii. IQia n considerare doar un singur tip de inteligen, inteligena cognitiv(mental). Ulterior ns, a fost scos n eviden un alt aspect al inteligenei

umane, inteligena emoional, care are la baz teoria inteligenelor multiple alui Gardner.


41/190


1.1.2. Inteligene multiple

Teoria inteligenelor multiplea fost formulat pentru prima oar de ctrepsihologul american Howard Gardner [Gar83]. Teoria sa pornete de la ideeaexistenei unor inteligene diferite i autonome ce conduc la modaliti diversede cunoatere, nelegere i nvare. El consider c inteligena nu este onsuire pus n lumin prin fore standard, ci capacitatea de a rezolva problemei de a dezvolta sau realiza produse n situaii concrete de via.

Astfel, capacitatea cognitiv a omului este descris printr-un set deabiliti, talente, deprinderi mentale pe care Gardner le numete ,,inteligene(iniial 7, apoi 8 i apoi a fost pomenit i a 9-a: [Gar06]). Toi indivizii normaliposed fiecare din aceste inteligene ntr-o msur mai mare sau mai mic. Ceeace-i deosebete este gradul lor de dezvoltare i natura unic a combinrii acestorinteligene la fiecare individ n parte. n acest sens Gardner subliniaz ideea co inteligen trebuie s fie probat de existena unei zone de reprezentare pecreier i prin existena unui sistem propriu de expresie.

Howard Gardner a identificat pn n prezent (n [Gar83] i [Gar06])

urmtoarele tipuri de inteligen:1. Inteligena lingvistic: capacitatea de a rezolva probleme i de a construi

produse cu ajutorul codului lingvistic (presupune abilitatea i plcerea de aciti, scrie, povesti sau a se juca cu cuvintele (exemple: rezolvareacuvintelor ncruciate, practicarea jocului SCRABLE etc.);

2. Inteligena logico-matematic: presupune capacitatea de a descoperilegturi, modele, categorii i relaii (exemple: se manifest n jocuri logice,rezolvarea problemelor de aritmetic sau n jocurile de strategie);

3. Inteligena spaial:se refer la capabilitatea de a gndi n imagini i lafacilitatea n rezolvarea unor probleme de tip geometrico-spaial (exemple:gsirea drumului ntr-un labirint, aptitudinea de a desena sau de a construi

figuri din cuburi Lego sau jocuri pe calculator de tip spaial);4. Inteligena corporal-kinestezic: implic o mare sensibilitate n

identificarea i prelucrarea senzaiilor fizice, de exemplu, a simi ritmulunui dans; inteligena la nivelul corpului i al minilor ne permite scontrolm i s interpretm micrile corpului, s manevrm obiecte, srealizm coordonarea (armonia) dintre trup i spirit. Acest tip deinteligen nu se regsete numai la atlei, acrobai sau dansatori, ci poatefi ntlnit n micrile, n practicarea unor meserii riscante care presupun omare finee pentru reuit (o operaie pe creier, dezamorsarea unei bombe,pilotarea unei maini de curse etc.). Acest tip de inteligen includedeprinderi fizice speciale precum coordonarea, echilibrul, dexteritatea,

fora, flexibilitatea, viteza, precum i deprinderi la nivelulproprioceptorilor, la nivel tactil i cutanat;


42/190


5. Inteligena muzical: presupune existena urechii muzicale, adic aposibilitii de a percepe i distinge sunete care par la fel altor persoane;

6. Inteligena interpersonal:presupune empatie (uurin de a te pune nsituaia altcuiva, adic existena capacitii de a nelege sentimentelealtora), este prezent mai ales la cei cu spirit de conductor;

7. Inteligena intrapersonal: reflect o bun cunoatere a propriilorsentimente i posibiliti, capacitate de introspecie i autoanaliz nonsubiectiv.

8. Inteligena naturalist (capacitatea de a rezolva probleme i de adezvolta produse cu ajutorul clasificrilor i reprezentrilor din mediulnconjurtor).

9. Inteligena existenial Gardner este convins c este o modalitate decunoatere a lumii care i caracterizeaz pe filozofi, pe cei care punntrebri despre sensul fericirii, nceputul universului etc. Probabil c ispiritualitatea aparine acestui tip de inteligen. Gardner ns nu a stabilitlocalizarea pe creier. De aceea vorbete despre aceasta ca despre ojumtate de inteligen.

Din punct de vedere biologic, inteligenele sunt independente, n funciede zonele corticale care le guverneaz. La nivel individual ele apar ncombinaii, fiecare individ fiind de fapt , o colecie de inteligene.

Un studiu recent elaborat de ctre Karl Albrecht [Alb06] menioneaznecesitatea rearanjrii modelului inteligenelor multipleal lui Howard Gardner,n alte ase categorii primare:

1. Inteligena abstract:raionamente simbolice;2. Inteligena social:legturile interumane;3. Inteligena practic:organizarea activitilor;4. Inteligena emoional:contiina de sine i auto-controlul;5. Inteligena estetic:sensul formelor, desenul, muzica,arta i literatura;

6. Inteligena kinestezic: capacitile fizice, cum ar fi cele sportive,dansul, muzica etc.

1.1.3. Inteligena cognitiv (IQ). Teste psihometrice pentru IQ

Se zice c IQ este un coeficient care nu poate fi ameliorat semnificativ peparcursul vieii. Testele de inteligen au fost folosite pentru a anticipa succesuleducaional. Astfel c persoanele cu un IQ sczut sunt uneori orientate ctre unprogram de educaie pentru persoane cu nevoi speciale, n timp ce un IQ ridicatrecomand aceste persoane pentru un program educaional avansat.

Preocuparea pentru realizarea unor teste ct mai exacte dateaz nc din

anul 1905 i se datoreaz psihologului francez Alfred Binet, care a publicatprimul test modern de evaluare a inteligenei, cunoscut azi sub numele de scalade inteligen Binet-Simon. Principalul scop al acestui test era de a identifica


43/190


studenii care aveau nevoie de asisten special n parcurgerea planului denvmnt. n colaborare cu Theodore Simon, Binet a adus optimizri,publicnd noi versiuni ale acestui test de evaluare a inteligentei n 1908 i 1911.

Abrevierea termenului de coeficient de inteligensau IQ (traducerea dingerman a Intelligenz-Quotient) a fost atribuit n 1912 unui psiholog german,William Stern,care definea IQ ca fiind coeficientul de msurare a nivelului deinteligen al unei persoane.

n 1916, Lewis M. Terman, profesor la Universitatea Stanford, aplicteoria lui Stern pentru o versiune rafinat a Scalei Binet-Simon i elaboreaz untest numit scala de inteligen Stanford-Binet. Testul lui Terman a pus bazeleunuia dintre cele mai moderne teste de evaluare a inteligentei folosit pn nprezent.

IQ se calcula folosind formulaIQ= 100 X vrsta mintal/vrsta biologic,

rezultnd c pentru o persoan n vrst de 10 ani care era evaluat la nivelulunei persoane cu vrsta de 13 ani s aib un IQ de 130 (100 X 13/10).

Primul test de inteligen special creat pentru aduli a fost publicat de abia

n 1939 deDavid Wechsleri era numit scala de inteligen pentru aduli a luiWeschler (WAIS), ceea ce a determinat i apariia WISC (scala de inteligenpentru minori a lui Weschler), standardiznd astfel coeficientul de inteligen,care nu se mai baza pe vrst.

Astfel, pe baza rezultatelor aplicrii acestui test, persoanele testate suntarondate unei anumite categorii de inteligen (v. fig. 1.1.1).

IQ CLASIFICARE>140 Geniu120-140 Deosebit de inteligent110-119 Foarte inteligent

90-109 Inteligen medie (Normal)80- 89 Inteligen mediocr70- 79 La limita deficienei mintale50-69 napoiat mintal (Cretin)20-49 Imbecil< 20 Idiot

Figura 1.1.1. Clasificarea inteligenei umane dup IQ

Faptul ca IQ msoar doar inteligena nnscuti nu poate fi amelioratsemnificativ pe parcursul vieii, dar i ncercrile de a explica situaiile n care

persoane cu un IQ mediu sau sczut au cunoscut un mare succes n societate (deexemplu, Shakespeare, Darwin, Spilberg, Picasso, Ghandi, Einstein, Mozart,Freud etc.), au deschis perspectivele teoriei privind importana i influena


44/190


inteligenei emoionale n dezvoltarea personalitii umane. Deci, inteligenaeste de dou tipuri: cea cognitiv (analitic, logic) i cea emoional. Primaeste strategic i acioneaz pe termen lung, iar cea de-a doua poate oferirspunsuri la probleme curente n viaa de zi cu zi.

1.1.4. Inteligena emoional (EQ). Inteligena social

Cartea lui Daniel Goleman, Inteligena emoional, cheia succesului nvia (v. [Gol04] i www.DanielGoleman.info), a marcat o revoluie uluitoaren psihologie prin analiza importanei covritoare a emoiilor n dezvoltareapersonalitii umane.

Studiul su ne explic cum, atunci cnd ne nelegem sentimentele,situaia n care ne aflm devine mai limpede. Descoperim chiar un nou mod dea privi cauzele bolilor care ne macin familia i societatea.Prelund rezultatele cercetrilor asupra creierului i comportamentului, autorulpropune extinderea conceptului de inteligen. Autorul a deschis calea uneipsihologii care acord un interes egal i inteligenei sentimentelor.

Inteligena emoional (EQ) presupune, n primul rnd, contientizarede sine, autodisciplin i empatie. Ea d seama de felul n care ne controlmimpulsurile i sentimentele.

Vestea bun este faptul c inteligena emoional poate fi mbuntit.Dei copilria este extrem de important n punerea unor baze solide pentrudezvoltarea inteligenei emoionale, ea poate fi mbuntit i cultivat inclusivla vrsta adult.

La zece ani de la apariia primei ediii n limba englez, studiulinteligenei emoionale a cptat proporiile unui domeniu tiinific autonom nslujba cruia lucreaz un numr impresionant de cercettori folosind cele maiavansate metode tehnologice. Astzi, inteligena emoional se pred n coli i

universiti, competenele sale au devenit criterii de angajare sau de promovaren carier, iar programele de educaie pe baza sa au devenit punctul de plecaren politicile sociale de prevenire a mbolnvirilor psihice sau criminalitii.

Mai mult, se vorbete azi deja i de o inteligen social. Omul este unanimal social, dup cum a spus nc Aristotel. Omul triete i acioneaz ntr-un mediu social. De aceea, eficiena sa att n rezolvarea problemelor din viaade zi cu zi, ct si a celor ntlnite n activitatea profesional, nu depinde numaide aptitudinea intelectual, ci i de capacitatea de a construi i dezvolta relaiiinterpersonale pozitive i armonioase, care s permit ndeplinirea elurilorpropuse.

O alt carte a lui Daniel Goleman, Inteligena social. Noua tiin a

relaiilor umane [Gol07], ne atrage atenia asupra unui nou tip de inteligen,diferit de inteligena emoional, nu ca parte a acesteia, ci ca dimensiune desine stttoare.


45/190


Reaciile pe care le avem fa de ceilali, ca i ale lor fa de noi, au unimpact biologic mult mai extins dect ne nchipuim. Este vorba de declanareaunor cascade de hormoni care ne regleaz ntregul organism, de la inim pn lasistemul imunitar, determinnd relaiile bune s acioneze ca nite vitamine, iarpe cele proaste ca nite otrvuri. Ne putem molipsi de emoiile celorlalioameni tot aa cum lum o grip, iar, pe de alt parte, consecinele izolrii saucele ale unui stres social intens ne pot scurta viaa.

n Inteligena social, Goleman explic surprinztoarea corectitudine aprimelor impresii, fundamentul carismei i fora emoional, complexitateaatraciei sexuale i sesizarea minciunilor. El descrie partea ntunecat ainteligenei sociale, de la narcisism la machiavelism i psihopatie. Ne maivorbete despre uimitoarea noastr capacitate de a fi vizionari, ca i despretragedia celor care, asemenea copiilor autiti, au un acces redus la raiune. Iarmesajul distinct al acestei cri este urmtorul: noi, oamenii, avem o predileciennscut ctre empatie, cooperare i altruism, astfel nct putem dezvolta ointeligen social prin care s ne hrnim aceste caliti nepreuite.

Suntem n era n care tot mai multe voci susin necesitatea dezvoltrii

acelei laturi a naturii umane care este inteligena emoional, cea care ne asigursuccesul profesional i n plan personal.

Modelul practic al competenei EQ elaborat de Daniel Goleman identificurmtoarele cinci dimensiuni:

1. Contiina de sine;2. Auto-cenzurarea;3. Motivaia;4. Empatia;5. Relaiile.

Steven J. Steini Howard E. Book[StB08] se refer la organizarea EQ sub

forma unor domenii:1. Domeniul intrapersonal: contiina emoional de sine, caracterul

asertiv, independena, respectul de sine, mplinirea de sine;2. Domeniul interpersonal: empatia, responsabilitatea social, relaiile

interpersonale;3. Domeniul adaptabilitii:testarea realitii, flexibilitatea, soluionarea

problemelor;4. Domeniul administrrii stresului: tolerana la stres, controlul

impulsurilor;5. Domeniul strii generale:optimismul, fericirea.


46/190


Modelul inteligenei sociale elaborat de ctre K. Albrecht [Alb06] estealctuit din cinci dimensiuni distincte:

1. Contiina situaional: radar social sau abilitatea de a studiasituaiile i de a interpreta comportamentul oamenilor;

2. Prezena: inuta sau ntreaga colecie de semnale pe care ceilali leproceseaz ntr-o impresie evaluatoare a unei persoane.

3. Autenticitatea: radarele sociale ale altora asupra comportamentuluinostru.

4. Claritatea: capacitatea noastr de ai face pe alii sa coopereze cu noi.5. Empatia: dar empatia mprtit ntre dou persoane, ca stare a

legturilor cu alt persoan care s creeze bazele pentru o interaciunepozitiv i cooperant.


47/190


1.2. Inteligena natural emergent a grupurilor sociale deanimale (swarm intelligence)

n natur ntlnim comportamente inteligente emergente la colonii de

furnici sau termite, roiuri de albine, stoluri de psri, turme de animale, haite delupi, etc.n general, vom prefera s numim acest tip de inteligen Swarm

Intelligence,denumire utilizat n limba englez pentru formele de inteligenartificial bazate pe comportamentul colectiv al sistemelor distribuite, auto-organizate din natur, ca cele amintite mai sus. Aceast expresie a fostintrodus de ctre Gerardo Beni i Jing Wang n 1989 n contextul sistemelorcelulare de roboi.

O alt definiiepentru Swarm Intelligence, care a fost dat de ctreBonabeau, Dorigo, Theraulaz, este: orice ncercare de a proiecta algoritmisau echipamente distribuite inspirate din comportamentul colectiv al coloniilor

de insecte sociale sau alte societi de animale, n [BDT01], [Ca+01],[HRR05]11.Unul dintre cele mai simple i mai relevante exemple de comportament

emergent inteligent l constituie, indiscutabil, coloniile de furnici.Cum creierul unei furnici cntrete mai puin de o milionime din

creierul uman, nu este de mirare c o specie de furnici poate produce doar zecepn la douzeci de semnale. Spre deosebire de limbajul uman, aceste mesajesunt integral instinctuale (Mark W. Moffett12, 2006).

O furnic are ntre 100 -10.000 neuroni (spre deosebire de om, care arecca. 100 de miliarde de neuroni). O furnic solitar este neajutorat i supuspieirii, dar n colonie furnicile dovedesc o inteligen de grup, de natur

emergent, uluitoare, rezolvnd n mod eficient problemele lor de via:construirea i gospodrirea muuroiului, cutarea hranei etc.Regina unei colonii de furnici (omoloaga mtcii unui stup de albine) are

doar rol de reproducere n colonie, ea nu d comenzi directe anumitor grupuride furnici pentru ca acestea s nceap s caute hran sau s construiasc, sntrein sau s apere muuroiul. Fiecare furnic, pe baza unui program genetic,reacioneaz la stimuli chimici generai de larve, de alte furnici sau de intrui ilas i ea o urm chimic deferomonicare reprezint un stimul pent

dzitac ia print-1

Documents