Discontinuous Recall Transitions Induced by Competition Between Short- and Long-Range Interactions in Recurrent Networks
Abstract
We present exact analytical equilibrium solutions for a class of recur(cid:173) rent neural network models, with both sequential and parallel neuronal dynamics, in which there is a tunable competition between nearest(cid:173) neighbour and long-range synaptic interactions. This competition is found to induce novel coexistence phenomena as well as discontinuous transitions between pattern recall states, 2-cycles and non-recall states.
Cite
Text
Skantzos et al. "Discontinuous Recall Transitions Induced by Competition Between Short- and Long-Range Interactions in Recurrent Networks." Neural Information Processing Systems, 1998.Markdown
[Skantzos et al. "Discontinuous Recall Transitions Induced by Competition Between Short- and Long-Range Interactions in Recurrent Networks." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/skantzos1998neurips-discontinuous/)BibTeX
@inproceedings{skantzos1998neurips-discontinuous,
title = {{Discontinuous Recall Transitions Induced by Competition Between Short- and Long-Range Interactions in Recurrent Networks}},
author = {Skantzos, N. S. and Beckmann, C. F. and Coolen, Anthony C. C.},
booktitle = {Neural Information Processing Systems},
year = {1998},
pages = {337-345},
url = {https://mlanthology.org/neurips/1998/skantzos1998neurips-discontinuous/}
}