Symmetries and learning in neural network models

Pierre BaldiPhysical 1987 · DOI

Abstract

I consider learning in neural network models and demonstrate how global properties can be derived from the characteristics of the local synaptic modification rules. I examine, in detail, the case of the Hopfield model of associative memory with Hebbian learning and show how the configuration space is partitioned into orbits of points of equal behavior, yielding a description of the structure of all the stable points. Calculations for a small-sized example are given.
BibTeX
@inproceedings{baldi1987symmetries,
  author = {Pierre Baldi},
  title = {{Symmetries and learning in neural network models}},
  booktitle = {Physical},
  year = {1987},
  doi = {10.1103/physrevlett.59.1976},
}

Loading related content...

Figure