神经网络的进化

Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI:10.1145/3583133.3595036

R. Miikkulainen

{"title":"神经网络的进化","authors":"R. Miikkulainen","doi":"10.1145/3583133.3595036","DOIUrl":null,"url":null,"abstract":"I . Original role (since 1990s): RL Tasks & especially POMDP I Both the structure and the weights evolved (no training) I Power from recurrency; behavior I . A new role (since 2016): Optimization of Deep Learning Nets I Architecture, hyperparameters, functions evolved; weights trained I Power from complexity I . A possible future role: Emergence of intelligence I Body/brain co-evolution; Competitive co-evolution I Evolution of memory, language, learning 3/62 I. Reinforcement Learning / POMDP Tasks","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evolution of Neural Networks\",\"authors\":\"R. Miikkulainen\",\"doi\":\"10.1145/3583133.3595036\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"I . Original role (since 1990s): RL Tasks & especially POMDP I Both the structure and the weights evolved (no training) I Power from recurrency; behavior I . A new role (since 2016): Optimization of Deep Learning Nets I Architecture, hyperparameters, functions evolved; weights trained I Power from complexity I . A possible future role: Emergence of intelligence I Body/brain co-evolution; Competitive co-evolution I Evolution of memory, language, learning 3/62 I. Reinforcement Learning / POMDP Tasks\",\"PeriodicalId\":422029,\"journal\":{\"name\":\"Proceedings of the Companion Conference on Genetic and Evolutionary Computation\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Companion Conference on Genetic and Evolutionary Computation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3583133.3595036\",\"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 of the Companion Conference on Genetic and Evolutionary Computation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3583133.3595036","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。最初的角色(自20世纪90年代以来):RL任务，特别是POMDP I结构和权重都是进化的(没有训练)I从递归中获得权力;行为;新角色(自2016年起):深度学习网络的优化I架构，超参数，功能演变;重量训练I从复杂性的力量I。未来可能的角色:智能的出现I体脑协同进化;3/62 .强化学习/ POMDP任务

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

Evolution of Neural Networks

I . Original role (since 1990s): RL Tasks & especially POMDP I Both the structure and the weights evolved (no training) I Power from recurrency; behavior I . A new role (since 2016): Optimization of Deep Learning Nets I Architecture, hyperparameters, functions evolved; weights trained I Power from complexity I . A possible future role: Emergence of intelligence I Body/brain co-evolution; Competitive co-evolution I Evolution of memory, language, learning 3/62 I. Reinforcement Learning / POMDP Tasks

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 of the Companion Conference on Genetic and Evolutionary Computation

自引率

0.00%

发文量