Quick search Find article
Quick search
Find article

Information capacity of a perceptron

N Brunel, J -P Nadal and G Toulouse

Show affiliations


The authors study the information storage capacity of a simple perceptron in the error regime. For random unbiased patterns the geometrical analysis gives a logarithmic dependence for the information content in the asymptotic limit. In this case, the statistical physics approach, when used at the simplest level of replica theory, does not give satisfactory results. However for perceptrons with finite stability, the information content can be simply calculated with statistical physics methods in a region above the critical storage level, for biased as well as for unbiased patterns.


PACS

07.05.Mh Neural networks, fuzzy logic, artificial intelligence

MSC

82C32 Neural nets (See also 68T05, 91E40, 92B20)

Subjects

Instrumentation and measurement

Dates

Issue 19 (7 October 1992)



View by subject




Export








Please login to access our web services, or create an account if you don't yet have one.

You must have cookies enabled in your web browser to be able to login.

Username
Password

Forgotten your password? Get a new one here.