Training a perceptron by a bit sequence: Storage capacity

Abstract

A perceptron is trained by a random bit sequence. In comparison to the corresponding classification problem, the storage capacity decreases to alpha_c=1.70\pm 0.02 due to correlations between input and output bits. The numerical results are supported by a signal to noise analysis of Hebbian weights.

LaTeX, 13 pages incl. 4 figures and 1 table

References in corpus (1)

• Storage of correlated patterns in a perceptron

Cited by in corpus (2)

• Limit cycles of a perceptron
• Competing neural networks: Finding a strategy for the game of matching pennies