Hopfield neural network simulation on a massively parallel machine

Domeika, Max; Page, Edward W.

doi:10.1016/0020-0255(95)00184-0

Cited by 1 publication

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the number of neurons is sufficiently large, the theoretical speedup factor is similar to the number of neurons. In [7], the authors propose some techniques which are specific for HNNs. They have observed that some neurons almost share the same evaluation expression.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Parallel Evaluation of Hopfield Neural Networks

2011

Proceedings of the International Conference on Neural Computation Theory and Applications

View full text Add to dashboard Cite

Among the large number of possible optimization algorithms, Hopfield Neural Networks (HNN) propose interesting characteristics for an in-line use. Indeed, this particular optimization algorithm can produce solutions in brief delay. These solutions are produced by the HNN convergence which was originally defined for a sequential evaluation of neurons. While this sequential evaluation leads to long convergence time, we assume that this convergence can be accelerated through the parallel evaluation of neurons. However, the original constraints do not any longer ensure the convergence of the HNN evaluated in parallel. This article aims to show how the neurons can be evaluated in parallel ensuring the convergence, in order to accelerate a hardware or multiprocessor implementation. The parallelisation method is illustrated on a simple task scheduling problem where we obtain an important acceleration related to the number of tasks. For instance, with a number of tasks equals to 20 the speedup factor is about 25.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In [7], several neurons are evaluated in parallel, on different processing units. Because, in general HNN implementations include more neurons than processing units, several sets of neurons are created.…”

Section: Related Workmentioning

confidence: 99%

Parallel Evaluation of Hopfield Neural Networks

2011

Proceedings of the International Conference on Neural Computation Theory and Applications

View full text Add to dashboard Cite

show abstract

Hopfield neural network simulation on a massively parallel machine

Cited by 1 publication

References 11 publications

Parallel Evaluation of Hopfield Neural Networks

Parallel Evaluation of Hopfield Neural Networks

Contact Info

Product

Resources

About