An Evaluation of the Dynamics of Diluted Neural Network
The Monte Carlo adaptation rule has been proposed to design asymmetric neural network. By adjusting the degree of the symmetry of the networks designed by this rule, the spurious memories or unwanted attractors of the networks can be suppressed completely. We have extended this rule to design full-c...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Atlantis Press
2016-12-01
|
Series: | International Journal of Computational Intelligence Systems |
Subjects: | |
Online Access: | https://www.atlantis-press.com/article/25868756/view |
id |
doaj-d74f3b08f51c42259f90e04a69e24b89 |
---|---|
record_format |
Article |
spelling |
doaj-d74f3b08f51c42259f90e04a69e24b892020-11-25T02:36:54ZengAtlantis PressInternational Journal of Computational Intelligence Systems 1875-68832016-12-019610.1080/18756891.2016.1256578An Evaluation of the Dynamics of Diluted Neural NetworkLijuan WangJun ShenQingguo ZhouZhihao ShangHuaming ChenHong ZhaoThe Monte Carlo adaptation rule has been proposed to design asymmetric neural network. By adjusting the degree of the symmetry of the networks designed by this rule, the spurious memories or unwanted attractors of the networks can be suppressed completely. We have extended this rule to design full-connected neural networks and diluted neural networks. Comparing the dynamics of these two neural networks, the simulation results indicated that the performance of diluted neural network was poorer than the performance of full-connected neural network. As to this point, further research is needed. In this paper, we use the annealed dilution method to design a diluted neural network with fixed degree of dilution. By analyzing the dynamics of the diluted neural network, it is verified that asymmetric full-connected neural network do have significant advantages over the asymmetric diluted neural network.https://www.atlantis-press.com/article/25868756/viewdiluted neural networkannealed dilutiondynamicsspurious memory |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lijuan Wang Jun Shen Qingguo Zhou Zhihao Shang Huaming Chen Hong Zhao |
spellingShingle |
Lijuan Wang Jun Shen Qingguo Zhou Zhihao Shang Huaming Chen Hong Zhao An Evaluation of the Dynamics of Diluted Neural Network International Journal of Computational Intelligence Systems diluted neural network annealed dilution dynamics spurious memory |
author_facet |
Lijuan Wang Jun Shen Qingguo Zhou Zhihao Shang Huaming Chen Hong Zhao |
author_sort |
Lijuan Wang |
title |
An Evaluation of the Dynamics of Diluted Neural Network |
title_short |
An Evaluation of the Dynamics of Diluted Neural Network |
title_full |
An Evaluation of the Dynamics of Diluted Neural Network |
title_fullStr |
An Evaluation of the Dynamics of Diluted Neural Network |
title_full_unstemmed |
An Evaluation of the Dynamics of Diluted Neural Network |
title_sort |
evaluation of the dynamics of diluted neural network |
publisher |
Atlantis Press |
series |
International Journal of Computational Intelligence Systems |
issn |
1875-6883 |
publishDate |
2016-12-01 |
description |
The Monte Carlo adaptation rule has been proposed to design asymmetric neural network. By adjusting the degree of the symmetry of the networks designed by this rule, the spurious memories or unwanted attractors of the networks can be suppressed completely. We have extended this rule to design full-connected neural networks and diluted neural networks. Comparing the dynamics of these two neural networks, the simulation results indicated that the performance of diluted neural network was poorer than the performance of full-connected neural network. As to this point, further research is needed. In this paper, we use the annealed dilution method to design a diluted neural network with fixed degree of dilution. By analyzing the dynamics of the diluted neural network, it is verified that asymmetric full-connected neural network do have significant advantages over the asymmetric diluted neural network. |
topic |
diluted neural network annealed dilution dynamics spurious memory |
url |
https://www.atlantis-press.com/article/25868756/view |
work_keys_str_mv |
AT lijuanwang anevaluationofthedynamicsofdilutedneuralnetwork AT junshen anevaluationofthedynamicsofdilutedneuralnetwork AT qingguozhou anevaluationofthedynamicsofdilutedneuralnetwork AT zhihaoshang anevaluationofthedynamicsofdilutedneuralnetwork AT huamingchen anevaluationofthedynamicsofdilutedneuralnetwork AT hongzhao anevaluationofthedynamicsofdilutedneuralnetwork AT lijuanwang evaluationofthedynamicsofdilutedneuralnetwork AT junshen evaluationofthedynamicsofdilutedneuralnetwork AT qingguozhou evaluationofthedynamicsofdilutedneuralnetwork AT zhihaoshang evaluationofthedynamicsofdilutedneuralnetwork AT huamingchen evaluationofthedynamicsofdilutedneuralnetwork AT hongzhao evaluationofthedynamicsofdilutedneuralnetwork |
_version_ |
1724798038724050944 |