Memory Properties of Non-Fully Interconnected Neural Network

• Authors: R.A. Kosiński , A. Zagórski
• Languages of publication: EN

Abstracts

EN

A model of a neural network consisting of two states neurons with the number N of (symmetric) synaptic connections per neuron treated as a variable was investigated numerically. Hebb's rule was used for storing uncorrelated patterns in the network. A maximal number of such patterns, which can be effectively retrieved by the network and the process of deterioration of the memory, is examined as a function of the number of synaptic connections per neuron. The influence of the number of neurons in the network as well as boundary conditions for the storage capacity of the network are discussed.

Keywords

EN

87.10.+e

• Publisher: Institute of Physics, Polish Academy of Sciences
• Journal: Acta Physica Polonica A
• Year: 1994
• Volume: 86
• Issue: 3
• Pages: 427-433

Dates

published

1994-05

received

1994-02-04

(unknown)

1994-05-13

Contributors

author

R.A. Kosiński

• Dept. of Applied Physics and Mathematics, Institute of Physics, Warsaw University of Technology, Koszykowa 75, 00-662 Warszawa, Poland

author

A. Zagórski

• Dept. of Applied Physics and Mathematics, Institute of Physics, Warsaw University of Technology, Koszykowa 75, 00-662 Warszawa, Poland