Competitive Learning: From Interactive Activation to Adaptive Resonance
Tóm tắt
Functional and mechanistic comparisons are made between several network models of cognitive processing: competitive learning, interactive activation, adaptive resonance, and back propagation. The starting point of this comparison is the article of Rumelhart and Zipser (1985) on feature discovery through competitive learning. All the models which Rumelhart and Zipser (1985) have described were shown in Grossberg (1976b) to exhibit a type of learning which is temporally unstable. Competitive learning mechanisms can be stabilized in response to an arbitrary input environment by being supplemented with mechanisms for learning top‐down expectancies, or templates; for matching bottom‐up input patterns with the top‐down expectancies; and for releasing orienting reactions in a mismatch situation, thereby updating short‐term memory and searching for another internal representation. Network architectures which embody all of these mechanisms were called adaptive resonance models by Grossberg (1976c). Self‐stabilizing learning models are candidates for use in real‐world applications where unpredictable changes can occur in complex input environments. Competitive learning postulates are inconsistent with the postulates of the interactive activation model of McClelland and Rumelhart (1981), and suggest different levels of processing and interaction rules for the analysis of word recognition. Adaptive resonance models use these alternative levels and interaction rules. The self‐organizing learning of an adaptive resonance model is compared and contrasted with the teacher‐directed learning of a back propagation model. A number of criteria for evaluating real‐time network models of cognitive processing are described and applied.
Từ khóa
Tài liệu tham khảo
Banquet J.‐P. &Grossberg S.(1987).Probing cognitive processes through the structure of event‐related potentials during learning: An experimental and theoretical analysis.Applied Optics.
Carpenter G.A. &Grossberg S.(1986).Associative learning adaptive pattern recognition and cooperative‐competitive decision making by neural networks. InH.Szu(Ed.)Hybrid and Optical Computing. SPIE Proceedings.
Carpenter G.A. &Grossberg S.(1987a).Neural dynamics of category learning and recognition: Attention memory consolidation and amnesia. InJ.Davis R.Newburgh &E.Wegman(Eds.) Brain structure learning and memory. AAAS Symposium Series.
Carpenter G.A. &Grossberg S.(1987c).Neural dynamics of category learning and recognition: Structural invariants reinforcement and evoked potentials. InM.L.Commons S.M.Kosslyn &R.J.Herrnstein(Eds.) Pattern recognition and concepts in animals people and machines.
Cohen M.A., 1986, Neural dynamics of speech and language coding: Developmental programs, perceptual grouping, and competition for short term memory, Human Neurobiology, 5, 1
Cohen M.A. &Grossberg S.(1987).Masking fields: A massively parallel neural architecture for learning recognizing and predicting multiple groupings of patterned data.Applied Optics.
Grossberg S., 1982, Competition and cooperation in neural networks, 263
Grossberg S., 1987, Pattern recognition by humans and machines, Vol. 1: Speech perception
Grossberg S., 1987, The adaptive brain, I: Cognition, learning, reinforcement, and rhythm
Grossberg S., 1987, The adaptive brain, II: Vision, speech, language, and motor control
Grossberg S. &Gutowski W.(1987).Neural dynamics of decision making under risk: Affective balance and cognitive‐emotional interactions.Psychological Review.
Grossberg S. &Levine D.S.(1987).Neural dynamics of attentionally modulated Pavlovian conditioning: Blocking inter‐stimulus interval and secondary reinforcement. Submitted for publication.
Kohonen T., 1984, Self‐organization and associative memory
McClelland J.L., 1981, An interactive activation model of context effects in letter perception, Part I: An account of basic findings, Psychological Review, 88, 375, 10.1037/0033-295X.88.5.375
Posner M.I., 1973, Cognition: An introduction
Rosenblatt F., 1962, Principles of neurodynamics
Rumelhart D.E., 1985, Institute for Cognitive Science Report 8506
Sejnowski T.J., 1986, NETtalk: A parallel‐network that learns to read aloud
Widrow B., 1962, Self‐organizing systems