Feed-Forward Chains of Recurrent Attractor Neural Networks Near Saturation
Abstract
We perform a stationary state replica analysis for a layered network of Ising spin neurons, with recurrent Hebbian interactions within each layer, in combination with strictly feed-forward Hebbian interactions between successive layers. This model interpolates between the fully recurrent and symmetric attractor network studied by Amit el al, and the strictly feed-forward attractor network studied by Domany et al. Due to the absence of detailed balance, it is as yet solvable only in the zero temperature limit. The built-in competition between two qualitatively different modes of operation, feed-forward (ergodic within layers) versus recurrent (non- ergodic within layers), is found to induce interesting phase transitions.
Keywords
Cite
@article{arxiv.cond-mat/9606200,
title = {Feed-Forward Chains of Recurrent Attractor Neural Networks Near Saturation},
author = {A. C. C. Coolen and L. Viana},
journal= {arXiv preprint arXiv:cond-mat/9606200},
year = {2009}
}
Comments
14 pages LaTex with 4 postscript figures submitted to J. Phys. A