多层神经网络中输者全输竞争的破坏性计算

R. Kamimura
{"title":"多层神经网络中输者全输竞争的破坏性计算","authors":"R. Kamimura","doi":"10.3233/his-230011","DOIUrl":null,"url":null,"abstract":"The present paper aims to propose a new learning method based on destructive computing, contrary to the conventional progressive computing or the steady-step learning. In spite of the existence of a large amount of biased or distorted information in inputs, the conventional learning methods fundamentally aim to gradually acquire information that is as faithful as possible to inputs, which has prevented us from acquiring intrinsic information hidden in the deepest level of inputs. At this time, it is permitted to suppose a leap to that level by changing information at hand not gradually but drastically. In particular, for the really drastic change of information, we introduce the winner-lose-all (WLA) to drastically destroy the supposedly most important information for immediately reaching or leaping to intrinsic information, hidden in complicated inputs. The method was applied to a target-marketing problem. The experimental results show that, with the new method, multi-layered neural networks had an ability to disentangle complicated network configurations into the simplest ones with simple and independent correlation coefficients between inputs and targets. This was realized by drastically changing the information content in the course of learning and, correspondingly, by mixing regular and irregular properties over connection weights.","PeriodicalId":88526,"journal":{"name":"International journal of hybrid intelligent systems","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Destructive computing with winner-lose-all competition in multi-layered neural networks\",\"authors\":\"R. Kamimura\",\"doi\":\"10.3233/his-230011\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The present paper aims to propose a new learning method based on destructive computing, contrary to the conventional progressive computing or the steady-step learning. In spite of the existence of a large amount of biased or distorted information in inputs, the conventional learning methods fundamentally aim to gradually acquire information that is as faithful as possible to inputs, which has prevented us from acquiring intrinsic information hidden in the deepest level of inputs. At this time, it is permitted to suppose a leap to that level by changing information at hand not gradually but drastically. In particular, for the really drastic change of information, we introduce the winner-lose-all (WLA) to drastically destroy the supposedly most important information for immediately reaching or leaping to intrinsic information, hidden in complicated inputs. The method was applied to a target-marketing problem. The experimental results show that, with the new method, multi-layered neural networks had an ability to disentangle complicated network configurations into the simplest ones with simple and independent correlation coefficients between inputs and targets. This was realized by drastically changing the information content in the course of learning and, correspondingly, by mixing regular and irregular properties over connection weights.\",\"PeriodicalId\":88526,\"journal\":{\"name\":\"International journal of hybrid intelligent systems\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International journal of hybrid intelligent systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3233/his-230011\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International journal of hybrid intelligent systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3233/his-230011","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

本文旨在提出一种新的基于破坏性计算的学习方法,与传统的渐进计算或稳态学习不同。尽管输入中存在大量有偏见或失真的信息,但传统的学习方法从根本上讲是为了逐步获得尽可能忠实于输入的信息,这使我们无法获得隐藏在输入最深层的内在信息。在这个时候,可以通过改变手头的信息来假设一个飞跃,不是逐渐的,而是急剧的。特别是,对于信息的真正剧烈变化,我们引入了赢家全输(WLA),以彻底破坏据称最重要的信息,从而立即到达或跳跃到隐藏在复杂输入中的内在信息。该方法被应用于一个目标营销问题。实验结果表明,使用新方法,多层神经网络能够将复杂的网络配置分解为输入和目标之间具有简单独立相关系数的最简单网络配置。这是通过在学习过程中大幅改变信息内容来实现的,相应地,通过在连接权重上混合规则和不规则属性来实现的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Destructive computing with winner-lose-all competition in multi-layered neural networks
The present paper aims to propose a new learning method based on destructive computing, contrary to the conventional progressive computing or the steady-step learning. In spite of the existence of a large amount of biased or distorted information in inputs, the conventional learning methods fundamentally aim to gradually acquire information that is as faithful as possible to inputs, which has prevented us from acquiring intrinsic information hidden in the deepest level of inputs. At this time, it is permitted to suppose a leap to that level by changing information at hand not gradually but drastically. In particular, for the really drastic change of information, we introduce the winner-lose-all (WLA) to drastically destroy the supposedly most important information for immediately reaching or leaping to intrinsic information, hidden in complicated inputs. The method was applied to a target-marketing problem. The experimental results show that, with the new method, multi-layered neural networks had an ability to disentangle complicated network configurations into the simplest ones with simple and independent correlation coefficients between inputs and targets. This was realized by drastically changing the information content in the course of learning and, correspondingly, by mixing regular and irregular properties over connection weights.
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
CiteScore
3.30
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信