利用Shapley值优化神经网络拓扑

2014 18th International Conference on System Theory, Control and Computing (ICSTCC) Pub Date : 2014-12-15 DOI:10.1109/ICSTCC.2014.6982527

F. Leon

{"title":"利用Shapley值优化神经网络拓扑","authors":"F. Leon","doi":"10.1109/ICSTCC.2014.6982527","DOIUrl":null,"url":null,"abstract":"The paper proposes a destructive method for optimizing the topology of neural networks based on the Shapley value, a game theoretic solution concept which estimates the contribution of each network element to the overall performance. More network elements can be simultaneously pruned, which can lead to shorter execution times and better results. An evolutionary hill climbing procedure is used to fine-tune the network after each simplification.","PeriodicalId":309866,"journal":{"name":"2014 18th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Optimizing neural network topology using Shapley value\",\"authors\":\"F. Leon\",\"doi\":\"10.1109/ICSTCC.2014.6982527\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The paper proposes a destructive method for optimizing the topology of neural networks based on the Shapley value, a game theoretic solution concept which estimates the contribution of each network element to the overall performance. More network elements can be simultaneously pruned, which can lead to shorter execution times and better results. An evolutionary hill climbing procedure is used to fine-tune the network after each simplification.\",\"PeriodicalId\":309866,\"journal\":{\"name\":\"2014 18th International Conference on System Theory, Control and Computing (ICSTCC)\",\"volume\":\"143 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-12-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2014 18th International Conference on System Theory, Control and Computing (ICSTCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSTCC.2014.6982527\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 18th International Conference on System Theory, Control and Computing (ICSTCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSTCC.2014.6982527","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 4

摘要

本文提出了一种基于Shapley值的神经网络拓扑优化的破坏性方法。Shapley值是一种博弈论解概念，用于估计每个网络元素对整体性能的贡献。可以同时修剪更多的网络元素，这可以缩短执行时间并获得更好的结果。在每次简化后，采用进化爬坡过程对网络进行微调。

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

Optimizing neural network topology using Shapley value

The paper proposes a destructive method for optimizing the topology of neural networks based on the Shapley value, a game theoretic solution concept which estimates the contribution of each network element to the overall performance. More network elements can be simultaneously pruned, which can lead to shorter execution times and better results. An evolutionary hill climbing procedure is used to fine-tune the network after each simplification.

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

2014 18th International Conference on System Theory, Control and Computing (ICSTCC)

自引率

0.00%

发文量