自联想Hopfield网络突触减少

2017 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON) Pub Date : 2017-09-01 DOI:10.1109/SIBIRCON.2017.8109860

M. Tarkov

{"title":"自联想Hopfield网络突触减少","authors":"M. Tarkov","doi":"10.1109/SIBIRCON.2017.8109860","DOIUrl":null,"url":null,"abstract":"Based on analogy with the oscillator networks, the auto-associative Hopfield network's behavior is investigated for the effect of reducing the connections number. It is shown that the exclusion of connections, with weights modules strictly less than the maximum for a given neuron, significantly improves the network performance. In this case, the allowed share of the distorted input vector elements increases with the network dimension.","PeriodicalId":135870,"journal":{"name":"2017 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Synapses reduction in autoassociative Hopfield network\",\"authors\":\"M. Tarkov\",\"doi\":\"10.1109/SIBIRCON.2017.8109860\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Based on analogy with the oscillator networks, the auto-associative Hopfield network's behavior is investigated for the effect of reducing the connections number. It is shown that the exclusion of connections, with weights modules strictly less than the maximum for a given neuron, significantly improves the network performance. In this case, the allowed share of the distorted input vector elements increases with the network dimension.\",\"PeriodicalId\":135870,\"journal\":{\"name\":\"2017 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)\",\"volume\":\"28 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SIBIRCON.2017.8109860\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIBIRCON.2017.8109860","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

在类比振荡器网络的基础上，研究了自关联Hopfield网络在减少连接数后的行为。结果表明，当权重模块严格小于给定神经元的最大值时，排除连接可以显著提高网络性能。在这种情况下，允许的扭曲输入向量元素的份额随着网络维度的增加而增加。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Synapses reduction in autoassociative Hopfield network

Based on analogy with the oscillator networks, the auto-associative Hopfield network's behavior is investigated for the effect of reducing the connections number. It is shown that the exclusion of connections, with weights modules strictly less than the maximum for a given neuron, significantly improves the network performance. In this case, the allowed share of the distorted input vector elements increases with the network dimension.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2017 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)

自引率

0.00%

发文量