创世纪网:使用强化学习的微调密集网络配置

Praveen Thachappully Adithya, R. Muthalagu, Sapna Sadhwani
{"title":"创世纪网:使用强化学习的微调密集网络配置","authors":"Praveen Thachappully Adithya, R. Muthalagu, Sapna Sadhwani","doi":"10.1145/3439133.3439139","DOIUrl":null,"url":null,"abstract":"Designing neural networks even in the case of relatively simpler fully connected neural networks / dense networks is a time-consuming process since the architecture design is done manually based on intuition and manual tweaking. In this paper, we present “Genesis Net”, a dense net that starts off with a very basic configuration (“seed configuration”), and subsequently tweaks itself via reinforcement learning (RL) to arrive at an optimal configuration for the task at hand. Genesis Net attained a test error within 0.59% of a similar but bigger documented baseline model. Furthermore, our model was able to achieve this using merely 10.11% of trainable weights that the baseline model used. This significantly smaller network was found using Q-Learning combined with a dynamic action space that allowed for fine tuning the network configuration.","PeriodicalId":291985,"journal":{"name":"2020 4th International Conference on Artificial Intelligence and Virtual Reality","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Genesis Net: Fine Tuned Dense Net Configuration using Reinforcement Learning\",\"authors\":\"Praveen Thachappully Adithya, R. Muthalagu, Sapna Sadhwani\",\"doi\":\"10.1145/3439133.3439139\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Designing neural networks even in the case of relatively simpler fully connected neural networks / dense networks is a time-consuming process since the architecture design is done manually based on intuition and manual tweaking. In this paper, we present “Genesis Net”, a dense net that starts off with a very basic configuration (“seed configuration”), and subsequently tweaks itself via reinforcement learning (RL) to arrive at an optimal configuration for the task at hand. Genesis Net attained a test error within 0.59% of a similar but bigger documented baseline model. Furthermore, our model was able to achieve this using merely 10.11% of trainable weights that the baseline model used. This significantly smaller network was found using Q-Learning combined with a dynamic action space that allowed for fine tuning the network configuration.\",\"PeriodicalId\":291985,\"journal\":{\"name\":\"2020 4th International Conference on Artificial Intelligence and Virtual Reality\",\"volume\":\"38 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 4th International Conference on Artificial Intelligence and Virtual Reality\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3439133.3439139\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 4th International Conference on Artificial Intelligence and Virtual Reality","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3439133.3439139","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

即使在相对简单的全连接神经网络/密集网络的情况下,设计神经网络也是一个耗时的过程,因为架构设计是基于直觉和手动调整手动完成的。在本文中,我们提出了“创世纪网”,这是一个密集的网络,它从一个非常基本的配置(“种子配置”)开始,随后通过强化学习(RL)调整自己,以达到手头任务的最佳配置。Genesis Net的测试误差与一个类似但更大的记录基线模型的测试误差在0.59%以内。此外,我们的模型仅使用基线模型使用的10.11%的可训练权重就能实现这一目标。这个小得多的网络是使用Q-Learning结合动态动作空间发现的,动态动作空间允许对网络配置进行微调。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Genesis Net: Fine Tuned Dense Net Configuration using Reinforcement Learning
Designing neural networks even in the case of relatively simpler fully connected neural networks / dense networks is a time-consuming process since the architecture design is done manually based on intuition and manual tweaking. In this paper, we present “Genesis Net”, a dense net that starts off with a very basic configuration (“seed configuration”), and subsequently tweaks itself via reinforcement learning (RL) to arrive at an optimal configuration for the task at hand. Genesis Net attained a test error within 0.59% of a similar but bigger documented baseline model. Furthermore, our model was able to achieve this using merely 10.11% of trainable weights that the baseline model used. This significantly smaller network was found using Q-Learning combined with a dynamic action space that allowed for fine tuning the network configuration.
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
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:604180095
Book学术官方微信