On Neurodynamics with Limiter Function and Linsker's Developmental Model
- 1 July 1996
- journal article
- Published by MIT Press in Neural Computation
- Vol. 8 (5) , 1003-1019
- https://doi.org/10.1162/neco.1996.8.5.1003
Abstract
The limiter function is used in many learning and retrieval models as the constraint controlling the magnitude of the weight or state vectors. In this paper, we developed a new method to relate the set of saturated fixed points to the set of system parameters of the models that use the limiter function, and then, as a case study, applied this method to Linsker's Hebbian learning network. We derived a necessary and sufficient condition to test whether a given saturated weight or state vector is stable or not for any given set of system parameters, and used this condition to determine the whole regime in the parameter space over which the given state is stable. This approach allows us to investigate the relative stability of the major receptive fields reported in Linsker's simulations, and to demonstrate the crucial role played by the synaptic density functions.Keywords
This publication has 11 references indexed in Scilit:
- The Role of Constraints in Hebbian LearningNeural Computation, 1994
- Stability and Optimization Analyses of the Generalized Brain-State-in-a-Box Neural Network ModelJournal of Mathematical Psychology, 1993
- Dynamical analysis of the brain-state-in-a-box (BSB) neural modelsIEEE Transactions on Neural Networks, 1992
- Derivation of Linear Hebbian Equations from a Nonlinear Hebbian Model of Synaptic PlasticityNeural Computation, 1990
- Analysis of Linsker's application of Hebbian rules to linear networksNetwork: Computation in Neural Systems, 1990
- Self-organization in a perceptual networkComputer, 1988
- Equilibria of the brain-state-in-a-box (BSB) neural modelNeural Networks, 1988
- From basic network principles to neural architecture: emergence of spatial-opponent cells.Proceedings of the National Academy of Sciences, 1986
- The “Brain-State-in-a-Box” neural model is a gradient descent algorithmJournal of Mathematical Psychology, 1986
- Distinctive features, categorical perception, and probability learning: Some applications of a neural model.Psychological Review, 1977