Category learning and adaptive pattern recognition: A neural network model

Author(s): Carpenter, G.A. | Grossberg, S. |

Year: 1985

Citation: Proceedings of the 3rd Army Conference on Applied Mathematics and Computing, ARO Report 86-1, 37-56.

Abstract: A theory is presented of how recognition categories can be learned in response to a temporal stream of input patterns. Interactions between an attentional subsystem and an orienting subsystem enable the network to self-stabilize its learning without an external teacher, as the code becomes globally self-consistent. Category learning is thus determined by global contextual information in this system. The attentional subsystem learns bottom-up codes and top-down templates, or expectancies. The internal representations formed in this way stabilize themselves against recoding by matching the learned top-down templates against input patterns. This matching process detects structural pattern properties in addition to local feature matches. The top-down templates can also suppress noise in the input patterns, and can subliminally prime the network to anticipate a set of input patterns. Mismatches activate an orienting subsystem, which resets incorrect codes and drives a rapid search for new or more appropriate codes. As the learned code becomes globally self-consistent, the orienting subsystem is automatically disengaged and the memory consolidates. After the recognition categories for a set of input patterns self-stabilize, those patterns directly access their categories without any search or recoding on future recognition trials. A novel pattern exemplar can directly access an established category if it shares invariant properties with the set of familiar exemplars that category. Several attentional and nonspecific arousal mechanisms modulate the course of search and l earning. Three types of attentional mechanism - priming, gain control, and vigilance ? are distinguished. Three types of nonspecific arousal are also mechanistically characterized. The nonspecific vigilance process determines how fine the learned categories will be. If vigilance increases due, for example, to a negative reinforcement, then the system automatically searches for and learns finer recognition categories. The learned top-down expectancies become more abstract as the recognition categories become broader. The learned code is a property of network interactions and the entire history of input pattern presentations. The interactions generate emergent rules such as a Weber Law Rule, a 2/3 Rule, and an Associative Decay Rule. No serial programs or algorithmic rule structures are used.

Topics: Biological Learning, Machine Learning, Models: Other,

PDF download




Cross References


  1. Neural dynamics of category learning and recognition: Attention, memory consolidation, and amnesia
    A theory is developed of how recognition categories can be learned in response to a temporal stream of input patterns. Interactions between an attentional subsystem and an orienting subsystem enable the network to ... Article Details

  2. Neural dynamics of word recognition and recall: Attentional priming, learning, and resonance
    Data and models about recognition and recall of words and non words are unified using a real-time network processing theory. Lexical decision and word frequency effect data are analyzed in terms of theoretical concepts that ... Article Details

  3. Neural dynamics of form perception: Boundary completion, illusory figures, and neon color spreading
    A real-time visual processing theory is used to analyze real and illusory contour formation, contour and brightness interactions, neon color spreading, complementary color induction, and filling-in of discounted illuminants ... Article Details

  4. Neural dynamics of speech and language coding: Developmental programs, perceptual grouping, and competition for short-term memory
    Summary. A computational theory of how an observer parses a speech stream into context-sensitive language representations is described. It is shown how temporal lists of events can be chunked into unitized repre~ntations, ... Article Details

  5. Pattern formation, contrast control, and oscillations in the short-term memory of shunting on-center off-surround networks
    The transformation of spatial patterns and their storage in short term memory by shunting neural networks are studied herein. Various mechanisms are described for real-time regulation of the amount of contrast with which a ... Article Details