库仑能量网络训练方案的改进

Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence Pub Date : 1996-11-16 DOI:10.1109/TAI.1996.560451

John F. Vassilopoulos, C. Koutsougeras

{"title":"库仑能量网络训练方案的改进","authors":"John F. Vassilopoulos, C. Koutsougeras","doi":"10.1109/TAI.1996.560451","DOIUrl":null,"url":null,"abstract":"We discuss the interesting perspective offered by the Coulomb Energy network and we identify certain disadvantages with the existing approach to training it. We address these problems by constraining its architecture (topology) and offer a derivation of the new associated training algorithm. We study further refinements of this algorithm. Most notably, existing genetic algorithms are employed as initial search techniques and simulation results are provided.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Refinements in training schemes for the Coulomb Energy network\",\"authors\":\"John F. Vassilopoulos, C. Koutsougeras\",\"doi\":\"10.1109/TAI.1996.560451\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We discuss the interesting perspective offered by the Coulomb Energy network and we identify certain disadvantages with the existing approach to training it. We address these problems by constraining its architecture (topology) and offer a derivation of the new associated training algorithm. We study further refinements of this algorithm. Most notably, existing genetic algorithms are employed as initial search techniques and simulation results are provided.\",\"PeriodicalId\":209171,\"journal\":{\"name\":\"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence\",\"volume\":\"32 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1996-11-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TAI.1996.560451\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TAI.1996.560451","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

我们讨论了库仑能量网络提供的有趣观点，并指出了现有训练方法的某些缺点。我们通过约束其结构(拓扑)来解决这些问题，并提供新的相关训练算法的推导。我们研究了该算法的进一步改进。最值得注意的是，采用现有的遗传算法作为初始搜索技术，并给出了仿真结果。

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

Refinements in training schemes for the Coulomb Energy network

We discuss the interesting perspective offered by the Coulomb Energy network and we identify certain disadvantages with the existing approach to training it. We address these problems by constraining its architecture (topology) and offer a derivation of the new associated training algorithm. We study further refinements of this algorithm. Most notably, existing genetic algorithms are employed as initial search techniques and simulation results are provided.

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

Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence

自引率

0.00%

发文量