Neural networks: learning and forgetting

Jean‐Pierre Nadal, G. Toulouse, Marc Mézard, J P Changeux, Severine DehaeneCambridge 1988 · DOI · OpenAlex

Abstract

Networks of formal neurons provide simple models for distributed, content addressable, fault-tolerant memory. Many numerical and analytical results have been obtained recently, especially on the Hopfield model (Hopfield, 1982). In this model, a network of a large number of fully connected neurons, with symmetric interactions, has a memory capacity which increases linearly with the size of the network – that is, in fact, with the connectivity. When the total number of stored patterns exceeds this capacity, a catastrophic deterioration occurs, as total confusion sets in. Alternative schemes have been proposed (Hopfield, 1982; Nadal et al., 1986; Parisi, 1986) that avoid overloading: new patterns can always be learned, at the expense of more anciently stored ones which get erased – for this reason, these schemes have been called palimpsest. Numerical and analytical results (Nadal et al., 1986; Mézard et al., 1986) detail the behavior of these models, which show striking analogies with the behavior of human short-term memory. We will review the main results, and point out the possible relevance for human working memory.
BibTeX
@inproceedings{nadal1988neural,
  author = {Jean‐Pierre Nadal and G. Toulouse and Marc Mézard and J P Changeux and Severine Dehaene},
  title = {{Neural networks: learning and forgetting}},
  booktitle = {Cambridge},
  year = {1988},
  doi = {10.1017/cbo9780511983467.014},
}

Loading related content...

Figure