Representational capacity of a set of independent neurons

Preprint

31 January 2002

preprint
Published by arXiv in arXiv

https://doi.org/10.48550/arXiv.cond-mat/0201588

Abstract

The capacity with which a system of independent neuron-like units represents a given set of stimuli is studied by calculating the mutual information between the stimuli and the neural responses. Both discrete noiseless and continuous noisy neurons are analyzed. In both cases, the information grows monotonically with the number of neurons considered. Under the assumption that neurons are independent, the mutual information rises linearly from zero, and approaches exponentially its maximum value. We find the dependence of the initial slope on the number of stimuli and on the sparseness of the representation.

Keywords

REPRESENTATIONAL CAPACITY
INDEPENDENT NEURON
MUTUAL INFORMATION
MONOTONICALLY
NEURON LIKE
LIKE UNITS
STIMULI
NEURONS

All Related Versions

Version 1, 2002-01-31, ArXiv

This publication has 0 references indexed in Scilit: