Using a map-based encoding to evolve plastic neural networks

Paul Tonelli, Jean-Baptiste Mouret
{"title":"Using a map-based encoding to evolve plastic neural networks","authors":"Paul Tonelli, Jean-Baptiste Mouret","doi":"10.1109/EAIS.2011.5945909","DOIUrl":null,"url":null,"abstract":"Many controllers for complex agents have been successfully generated by automatically desiging artificial neural networks with evolutionary algorithms. However, typical evolved neural networks are not able to adapt themselves online, making them unable to perform tasks that require online adaptation. Nature solved this problem on animals with plastic nervous systems. Inpired by neuroscience models of plastic neural-network, the present contribution proposes to use a combination of Hebbian learning, neuro-modulation and a a generative map-based encoding. We applied the proposed approach on a problem from operant conditioning (a Skinner box), in which numerous different association rules can be learned. Results show that the map-based encoding scaled up better than a classic direct encoding on this task. Evolving neural networks using a map-based generative encoding also lead to networks that works with most rule sets even when the evolution is done on a small subset of all the possible cases. Such a generative encoding therefore appears as a key to improve the generalization abilities of evolved adaptive neural networks.","PeriodicalId":243348,"journal":{"name":"2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS)","volume":"198200 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EAIS.2011.5945909","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11

Abstract

Many controllers for complex agents have been successfully generated by automatically desiging artificial neural networks with evolutionary algorithms. However, typical evolved neural networks are not able to adapt themselves online, making them unable to perform tasks that require online adaptation. Nature solved this problem on animals with plastic nervous systems. Inpired by neuroscience models of plastic neural-network, the present contribution proposes to use a combination of Hebbian learning, neuro-modulation and a a generative map-based encoding. We applied the proposed approach on a problem from operant conditioning (a Skinner box), in which numerous different association rules can be learned. Results show that the map-based encoding scaled up better than a classic direct encoding on this task. Evolving neural networks using a map-based generative encoding also lead to networks that works with most rule sets even when the evolution is done on a small subset of all the possible cases. Such a generative encoding therefore appears as a key to improve the generalization abilities of evolved adaptive neural networks.
使用基于地图的编码来进化塑性神经网络
利用进化算法自动设计人工神经网络,已经成功地生成了许多复杂智能体的控制器。然而,典型的进化神经网络不能在线自我适应,这使得它们无法执行需要在线适应的任务。大自然在具有可塑性神经系统的动物身上解决了这个问题。受可塑性神经网络的神经科学模型的启发,本论文提出结合Hebbian学习、神经调节和基于生成地图的编码。我们将提出的方法应用于操作性条件反射问题(斯金纳箱),其中可以学习许多不同的关联规则。结果表明,基于映射的编码比经典的直接编码在该任务上有更好的扩展。使用基于地图的生成编码的进化神经网络也会导致网络与大多数规则集一起工作,即使进化是在所有可能情况的一小部分上完成的。因此,这种生成式编码似乎是提高进化的自适应神经网络泛化能力的关键。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
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