Adaptive pattern classification and universal recoding: I Parallel development and coding of neural feature detectors

Author(s): Grossberg, S. |

Year: 1976

Citation: Biol Cybern Volume: 23 Issue: 3 Pages: 121-34

Abstract: This paper analyses a model for the parallel development and adult coding of neural feature detectors. The model was introduced in Grossberg (1976). We show how experience can retune feature detectors to respond to a prescribed convex set of spatial patterns. In particular, the detectors automatically respond to average features chosen from the set even if the average features have never been experienced. Using this procedure, any set of arbitrary spatial patterns can be recoded, or transformed, into any other spatial patterns (universal recoding), if there are sufficiently many cells in the network s cortex. The network is built from short term memory (STM) and long term memory (LTM) mechanisms, including mechanisms of adaptation, filtering, contrast enhancement, tuning, and nonspecific arousal. These mechanisms capture some experimental properties of plasticity in the kitten visual cortex. The model also suggests a classification of adult feature detector properties in terms of a small number of functional principles. In particular, experiments on retinal dynamics, including amarcrine cell function, are suggested.

Topics: Biological Vision, Mathematical Foundations of Neural Networks, Models: Other,

PDF download




Cross References


  1. Neural pattern discrimination
    Some possible neural mechanisms of pattern discrimination are discussed, leading to neural networks which can discriminate any number of essentially arbitrarily complicated space-time patterns and activate cells which can ... Article Details

  2. Nonlinear difference-differential equations in prediction and learning theory
    Introduction.-This note introduces some nonlinear difference-differential equations which can be interpreted as a learning theory or, alternatively, as a prediction theory whose goal is to discuss the prediction of ... Article Details

  3. Neural expectation: Cerebellar and retinal analogs of cells fired by learnable or unlearned pattern classes
    Neural networks are introduced which can be taught by classical or instrumental conditioning to fire in response to arbitrary learned classes of patterns. The filters of output cells are biased by presetting cells whose ... Article Details

  4. Contour enhancement, short-term memory, and constancies in reverberating neural networks
    A model of the nonlinear dynamics of reverberating on-center off-surround networks of nerve cells, or of cell populations, is analysed. The on-center off-surround anatomy allows patterns to be processed across populations ... Article Details

  5. Classical and instrumental learning by neural networks
    This article reviews results chosen from the theory of embedding fields. Embedding field theory discusses mechanisms of pattern discrimination and learning in a psychophysiological setting. It is derived from psychological ... Article Details