Discrete-time convergence theory and updating rules for neural networks with energy functions

Authors:
Lipo Wang
Affiliations:
Sch. of Comput. & Math., Deakin Univ., Clayton, Vic.
Venue:
IEEE Transactions on Neural Networks
Year:
1997

Citing 0
Cited 4

Modelling competitive Hopfield networks for the maximum clique problem

Computers and Operations Research
A Study into the Improvement of Binary Hopfield Networks for Map Coloring

ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
Letter: A binary Hopfield neural network with hysteresis for large crossbar packet-switches

Neurocomputing
Letter: Applications of a neural network to watermarking capacity of digital image

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present convergence theorems for neural networks with arbitrary energy functions and discrete-time dynamics for both discrete and continuous neuronal input-output-functions. We discuss systematically how the neuronal updating rule should be extracted once an energy function is constructed for a given application, in order to guarantee the descent and minimization of the energy function as the network updates. We explain why the existing theory may lead to inaccurate results and oscillatory behaviors in the convergence process. We also point out the reason for and the side effects of using hysteresis neurons to suppress these oscillatory behaviors