The dual of the space of interactions in neural network models

De Martino D. 2016. The dual of the space of interactions in neural network models. International Journal of Modern Physics C. 27(6), 1650067.

Download (ext.)

Journal Article | Published | English

Scopus indexed
Department
Abstract
In this work, the Gardner problem of inferring interactions and fields for an Ising neural network from given patterns under a local stability hypothesis is addressed under a dual perspective. By means of duality arguments, an integer linear system is defined whose solution space is the dual of the Gardner space and whose solutions represent mutually unstable patterns. We propose and discuss Monte Carlo methods in order to find and remove unstable patterns and uniformly sample the space of interactions thereafter. We illustrate the problem on a set of real data and perform ensemble calculation that shows how the emergence of phase dominated by unstable patterns can be triggered in a nonlinear discontinuous way.
Publishing Year
Date Published
2016-06-01
Journal Title
International Journal of Modern Physics C
Publisher
World Scientific Publishing
Volume
27
Issue
6
Article Number
1650067
IST-REx-ID

Cite this

De Martino D. The dual of the space of interactions in neural network models. International Journal of Modern Physics C. 2016;27(6). doi:10.1142/S0129183116500674
De Martino, D. (2016). The dual of the space of interactions in neural network models. International Journal of Modern Physics C. World Scientific Publishing. https://doi.org/10.1142/S0129183116500674
De Martino, Daniele. “The Dual of the Space of Interactions in Neural Network Models.” International Journal of Modern Physics C. World Scientific Publishing, 2016. https://doi.org/10.1142/S0129183116500674.
D. De Martino, “The dual of the space of interactions in neural network models,” International Journal of Modern Physics C, vol. 27, no. 6. World Scientific Publishing, 2016.
De Martino D. 2016. The dual of the space of interactions in neural network models. International Journal of Modern Physics C. 27(6), 1650067.
De Martino, Daniele. “The Dual of the Space of Interactions in Neural Network Models.” International Journal of Modern Physics C, vol. 27, no. 6, 1650067, World Scientific Publishing, 2016, doi:10.1142/S0129183116500674.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data ISTA Research Explorer

Sources

arXiv 1505.02963

Search this title in

Google Scholar