Energy Minimum Regularization in Continual Learning

Xiaobin Li, Lianlei Shan, Minglong Li, Weiqiang Wang
{"title":"Energy Minimum Regularization in Continual Learning","authors":"Xiaobin Li, Lianlei Shan, Minglong Li, Weiqiang Wang","doi":"10.1109/ICPR48806.2021.9412744","DOIUrl":null,"url":null,"abstract":"How to give agents the ability of continuous learning like human and animals is still a challenge. In the regularized continual learning method OWM, the constraint of the model on the energy compression of the learned task is ignored, which results in the poor performance of the method on the dataset with a large number of learning tasks. In this paper, we propose an energy minimization regularization(EMR) method to constrain the energy of learned tasks, providing enough learning space for the following tasks that are not learned, and increasing the capacity of the model to the number of learning tasks. A large number of experiments show that our method can effectively increase the capacity of the model and reduce the sensitivity of the model to the number of tasks and the size of the network.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"129 1","pages":"6404-6409"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 25th International Conference on Pattern Recognition (ICPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICPR48806.2021.9412744","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

How to give agents the ability of continuous learning like human and animals is still a challenge. In the regularized continual learning method OWM, the constraint of the model on the energy compression of the learned task is ignored, which results in the poor performance of the method on the dataset with a large number of learning tasks. In this paper, we propose an energy minimization regularization(EMR) method to constrain the energy of learned tasks, providing enough learning space for the following tasks that are not learned, and increasing the capacity of the model to the number of learning tasks. A large number of experiments show that our method can effectively increase the capacity of the model and reduce the sensitivity of the model to the number of tasks and the size of the network.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
持续学习中的能量最小正则化
如何赋予智能体像人类和动物一样的持续学习能力仍然是一个挑战。在正则化连续学习方法OWM中,忽略了模型对学习任务能量压缩的约束,导致该方法在具有大量学习任务的数据集上性能不佳。在本文中,我们提出了一种能量最小化正则化(EMR)方法来约束学习任务的能量,为后续未学习的任务提供足够的学习空间,并将模型的容量增加到学习任务的数量。大量实验表明,我们的方法可以有效地提高模型的容量,降低模型对任务数量和网络规模的敏感性。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Trajectory representation learning for Multi-Task NMRDP planning Semantic Segmentation Refinement Using Entropy and Boundary-guided Monte Carlo Sampling and Directed Regional Search A Randomized Algorithm for Sparse Recovery An Empirical Bayes Approach to Topic Modeling To Honor our Heroes: Analysis of the Obituaries of Australians Killed in Action in WWI and WWII
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1