Chaotic Boltzmann machines
Open Access
- 5 April 2013
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 3 (1) , srep01610
Abstract
The chaotic Boltzmann machine proposed in this paper is a chaotic pseudo-billiard system that works as a Boltzmann machine. Chaotic Boltzmann machines are shown numerically to have computing abilities comparable to conventional (stochastic) Boltzmann machines. Since no randomness is required, efficient hardware implementation is expected. Moreover, the ferromagnetic phase transition of the Ising model is shown to be characterised by the largest Lyapunov exponent of the proposed system. In general, a method to relate probabilistic models to nonlinear dynamics by derandomising Gibbs sampling is presented.Keywords
This publication has 50 references indexed in Scilit:
- High-Performance Reconfigurable Hardware Architecture for Restricted Boltzmann MachinesIEEE Transactions on Neural Networks, 2010
- An exact hardware implementation of the Boltzmann machine2003
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- Boltzmann machine neural network devices using single-electron tunnellingNanotechnology, 2001
- Boltzmann machine neuron device using quantum-coupled single electronsApplied Physics Letters, 1998
- Boltzmann machine neuron circuit using single-electron tunnelingApplied Physics Letters, 1997
- Combinatorial optimization on a Boltzmann machineJournal of Parallel and Distributed Computing, 1989
- Deterministic Boltzmann Learning Performs Steepest Descent in Weight-SpaceNeural Computation, 1989
- A Learning Algorithm for Boltzmann Machines*Cognitive Science, 1985
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1984