Learning by a neural net in a noisy environment—the pseudo-inverse solution revisited

A recurrent neural net is studied that learns a set of patterns {ξμ} in the presence of noise. The learning rule is of a Hebbian type. It is well-known that, if noise is absent during the learning process, the resulting final values of the weights wij correspond to what is usually referred to as the pseudo-inverse solution of the fixed point equation associated with the learning rule. In the limit of vanishing noise, the expressions derived in this article for the expectation value of the weights do not converge to the usual pseudo-inverse solution, in contrast to what one might expect. Since biological systems in general are noisy, the usual pseudo-inverse solution is less realistic, in principle, than the solution found in this article.

• Publication year

  2002

• Venue

  Physica A-statistical Mechanics and Its Applications

• Publication date

  2002-05-27

• Fields of study

  Biology, Physics, Computer Science, Mathematics, Psychology

• Identifiers
  DOI 10.1016/S0378-4371(02)01518-2arXiv cond-mat/0205550
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A recurrent neural network with ever changing synapses

  2000cited by this paper
• Derivation of Hebb's rule

  1999cited by this paper
• Neural networks optimally trained with noisy data.

  1993cited by this paper
• Neural networks: an introduction

  1990influential reference
• Training noise adaptation in attractor neural networks

  1990cited by this paper
• Optimally adapted attractor neural networks in the presence of noise

  1990cited by this paper
• Training with noise and the storage of correlated patterns in a neural network model

  1989cited by this paper
• The space of interactions in neural network models

  1988cited by this paper
• Models of neural networks

  1987cited by this paper
• Learning of correlated patterns in spin-glass networks by local learning rules.

  1987cited by this paper
• Information storage and retrieval in spin-glass like neural networks

  1985cited by this paper

• No citing papers are available for this paper.