Εισαγωγή στην Υπολογιστική Νοημοσύνη

Download Εισαγωγή στην Υπολογιστική Νοημοσύνη

Post on 30-Dec-2015

31 views

Category:

Documents

0 download

Embed Size (px)

DESCRIPTION

. . . () (Artificial Intelligence - AI ). ; . . - PowerPoint PPT Presentation

TRANSCRIPT

  • .

  • () (Artificial Intelligence - AI) ;

    .

    .

    , .

  • ; Terman .

    , .

    , , , , , ...

    ___________________________________________________________________________________________* Terman L. (1916). The uses of intelligence tests. n The measurement of intelligence. Boston, Houghton Mifflin.

  • , , , .

    :

    , , , , , , , , , .

  • , , , , , .

    , .

    .

  • , , () . .

    Gardner* , (, -, -, -, , , )._________________________________________________________________________________* Gardner H. (1983). Frames of Mind: A Theory of Multiple Intelligences. New York. Basic Books, 1983.

  • ( ), (distributed representation and processing) (connectionism) [(Rumelhart and McClelland, 1986); (Churchland and Sejnowski, 1992)].

    , .

  • , - (functional-computational intelligent systems), .

    (emerging properties), , .

    , ( ). , .

  • , , () (robustness) .

    , , ...

    .

  • , .

    , , .

    , .

    , ( ) () - .

  • (physical systems symbol hypothesis) Newell Simon, (language).

    / Chomski, Minsky, Fodor Pylyshyn).

    .

  • , , , .

  • (TN) / . / . (symbolic AI) , ( ). Dennet, Newell Simon, Chomski, Minsky, Fodor Pylyshyn (connectionism) - .. . , , / . Smolensky Hameroff.

  • - .

    .

  • O Marks (1994)* : , .*Marks R. 1993 Intelligence: computational versus artificial. IEEE Transactions on Neural Networks

  • Computational Intelligence: Concepts to Implementations by Eberhart and Shi

  • :

    (adaptation )

    - (self-organization )

    -

  • -

    1: : .

    2: : a: .b: .

    :

    : .

  • : syn:

    : , . syn:

    . -

  • . Adaptation is any process whereby a structure is progressively modified to give better performance in its environment. Holland 1992

    .

  • . (supervised adaptation) (, )

    (unsupervised adaptation)

    - (reinforcement adaptation)

  • (supervised adaptation) . .

    The process of adjusting (adapting) a system so it produces specified outputs in response to specified inputs." "Supervised means that the output is known for all inputs and the system training algorithm uses the error to guide the training. (Reed and Marks 1999)

  • Supervised Adaptation

  • Supervised Adaptation

    .

    (Fitness)

    : Back-propagation .

  • : - (reinforcement adaptation) , . .

    : .

  • Reinforcement Adaptation

  • Reinforcement Adaptation .

    (dynamic programming)

    .

    .

    : Particle swarm optimization

  • - (Unsupervised Adaptation): . . (Reed and Marks 1999)

    .

    : SOFM and LVQ networks (clustering)

  • Unsupervised Adaptation

  • : .( )

    ( )

    ( 0 1) .

  • - (Self-Organization) :

    .

    - Bonabeau:

    A set of dynamical mechanisms whereby structures appear at the global level of a system from interactions among its lower-level components. The rules specifying the interactions among the systems constituent units are executed on the basis of purely local information, without reference to the global pattern, which is an emergent property of the system rather than a property imposed on the system by an external ordering influence.

    : Formation of ice crystals, salt crystals. Cellular automata. The human brain.

  • -

    (animals and humans)

  • * - .

    .

    . .*Kauffman, S. A. 1993. The Origins if Order. New York : Oxford university press

  • .

    .

    - .

    evolution = natural selection + self organization

  • computational intelligence James Bezdek (1992)

    IEEE World Congress on Computational Intelligence 1994

    1996

    IEEE World Congress on CI in Anchorage 1998

    World Congresses in Hawaii (2002), Vancouver (2006)Hong Kong (2008)

  • Computational Intelligence 80 .

    Bezdek 1992 : Int. Jour. Approximate Reasoning.

    - pattern recognition)

  • Bezdek (1994) (). A system is computationally intelligent when it:

    Deals only with numerical (low-level) data, has a pattern recognition component, does not use knowledge in the AI sense; and additionally, when it (begins to) exhibit (i) computational adaptivity; (ii) computational fault tolerance; (iii) speed approaching human-like turnaround, and (iv) error rates that approximate human performance.

  • Bezdek:

  • Bezdek:

  • PedryczComputational intelligence (CI) is a recently emerging area of fundamental and applied research exploiting a number of advanced information processing technologies. The main components of CI encompass neural networks, fuzzy set technology and evolutionary computation. In this triumvirate, each of them plays an important, well-defined, and unique role. (Pedrycz 1998)

  • . -, .

  • . .

    * * /

  • .

  • .

  • Computational Intelligence provides success stories that are often hard to justify with formal mathematical models (which are but a subset of all computational models, some of which are based on mathematics, and some of which are not).- Jim Bezdek

  • (Artificial neural networks)

    (Expert systems) (Rule-based, Case-based)

    (Artificial life)

    (Genetic algorithms)

    (Fuzzy logic)

    Costas Neocleous - Costas Neocleous - , .