Self-control in Sparsely Coded Networks

Abstract

A complete self-control mechanism is proposed in the dynamics of neural networks through the introduction of a time-dependent threshold, determined in function of both the noise and the pattern activity in the network. Especially for sparsely coded models this mechanism is shown to considerably improve the storage capacity, the basins of attraction and the mutual information content of the network.

4 pages, 6 Postscript figures

Cited by in corpus (11)

• Retrieval dynamics of neural networks for sparsely coded sequential patterns
• An optimal Q-state neural network using mutual information
• Thresholds in layered neural networks with variable activity
• Mutual information and self-control of a fully-connected low-activity neural network
• Analysis of Oscillator Neural Networks for Sparsely Coded Phase Patterns
• Dynamical properties of a randomly diluted neural network with variable activity
• A layered neural network with three-state neurons optimizing the mutual information
• The three-state layered neural network with finite dilution
• Adaptive thresholds for neural networks with synaptic noise
• Mutual Information of Three-State Low Activity Diluted Neural Networks with Self-Control
• Self-control dynamics for sparsely coded networks with synaptic noise