Landscape statistics of the binary perceptron
- 1 January 1990
- journal article
- Published by EDP Sciences in Journal de Physique
- Vol. 51 (13) , 1403-1413
- https://doi.org/10.1051/jphys:0199000510130140300
Abstract
The landscape of the binary perceptron is studied by Simulated Annealing, exhaustive search and performing random walks on the landscape. We find that the number of local minima increases exponentially with the number of bonds, becoming deeper in the vicinity of a global minimum, but more and more shallow as we move away from it. The random walker detects a simple dependence on the size of the mapping, the architecture introducing a nontrivial dependence on the number of stepsKeywords
This publication has 4 references indexed in Scilit:
- Statistical mechanics model of protein folding : short and long chains have different folding transitionsJournal de Physique, 1989
- Perceptron beyond the limit of capacityJournal de Physique, 1989
- Learning times of neural networks: Exact solution for a PERCEPTRON algorithmPhysical Review A, 1988
- Optimization by Simulated AnnealingScience, 1983