Associative memory with high information content

Joachim M. Buhmann, R. Divko, Klaus SchultenPhysical 1989 · DOI

Abstract

An extension of Hopfield's model with adaptive threshold and inhibitory interactions yields a network capable of nearly optimal storage of patterns of low activity. A replica symmetric solution of the mean-field equations is presented for the noise-free case. The following properties are demonstrated: For a low level of activity a the storage capacity increases as -(a lna${)}^{\mathrm{\ensuremath{-}}1}$; up to 0.38 bits per synapse can be stored; spurious states can be suppressed; the network is not opinionated, i.e., it can categorize inputs as not similar enough to patterns stored.
BibTeX
@inproceedings{buhmann1989associative,
  author = {Joachim M. Buhmann and R. Divko and Klaus Schulten},
  title = {{Associative memory with high information content}},
  booktitle = {Physical},
  year = {1989},
  doi = {10.1103/physreva.39.2689},
}

Loading related content...

Figure