展望未来的深度学习理论:一些基本概念和特征

IF 7.3 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Weijie J. Su
{"title":"展望未来的深度学习理论:一些基本概念和特征","authors":"Weijie J. Su","doi":"10.1007/s11432-023-4129-1","DOIUrl":null,"url":null,"abstract":"<p>To advance deep learning methodologies in the next decade, a theoretical framework for reasoning about modern neural networks is needed. While efforts are increasing toward demystifying why deep learning is so effective, a comprehensive picture remains lacking, suggesting that a better theory is possible. We argue that a future deep learning theory should inherit three characteristics: a hierarchically structured network architecture, parameters iteratively optimized using stochastic gradient-based methods, and information from the data that evolves compressively. As an instantiation, we integrate these characteristics into a graphical model called neurashed. This model effectively explains some common empirical patterns in deep learning. In particular, neurashed enables insights into implicit regularization, information bottleneck, and local elasticity. Finally, we discuss how neurashed can guide the development of deep learning theories.</p>","PeriodicalId":21618,"journal":{"name":"Science China Information Sciences","volume":"28 1","pages":""},"PeriodicalIF":7.3000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Envisioning future deep learning theories: some basic concepts and characteristics\",\"authors\":\"Weijie J. Su\",\"doi\":\"10.1007/s11432-023-4129-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>To advance deep learning methodologies in the next decade, a theoretical framework for reasoning about modern neural networks is needed. While efforts are increasing toward demystifying why deep learning is so effective, a comprehensive picture remains lacking, suggesting that a better theory is possible. We argue that a future deep learning theory should inherit three characteristics: a hierarchically structured network architecture, parameters iteratively optimized using stochastic gradient-based methods, and information from the data that evolves compressively. As an instantiation, we integrate these characteristics into a graphical model called neurashed. This model effectively explains some common empirical patterns in deep learning. In particular, neurashed enables insights into implicit regularization, information bottleneck, and local elasticity. Finally, we discuss how neurashed can guide the development of deep learning theories.</p>\",\"PeriodicalId\":21618,\"journal\":{\"name\":\"Science China Information Sciences\",\"volume\":\"28 1\",\"pages\":\"\"},\"PeriodicalIF\":7.3000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Science China Information Sciences\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s11432-023-4129-1\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Science China Information Sciences","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11432-023-4129-1","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

为了在下一个十年推进深度学习方法,我们需要一个理论框架来推理现代神经网络。虽然越来越多的人在努力揭开深度学习为何如此有效的神秘面纱,但仍然缺乏一个全面的图景,这表明有可能出现更好的理论。我们认为,未来的深度学习理论应继承三个特点:分层结构的网络架构、使用基于随机梯度的方法迭代优化的参数以及压缩演化的数据信息。作为实例化,我们将这些特征整合到一个名为 neurashed 的图形模型中。该模型能有效解释深度学习中一些常见的经验模式。特别是,neurashed 能让我们深入了解隐式正则化、信息瓶颈和局部弹性。最后,我们将讨论 neurashed 如何指导深度学习理论的发展。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Envisioning future deep learning theories: some basic concepts and characteristics

To advance deep learning methodologies in the next decade, a theoretical framework for reasoning about modern neural networks is needed. While efforts are increasing toward demystifying why deep learning is so effective, a comprehensive picture remains lacking, suggesting that a better theory is possible. We argue that a future deep learning theory should inherit three characteristics: a hierarchically structured network architecture, parameters iteratively optimized using stochastic gradient-based methods, and information from the data that evolves compressively. As an instantiation, we integrate these characteristics into a graphical model called neurashed. This model effectively explains some common empirical patterns in deep learning. In particular, neurashed enables insights into implicit regularization, information bottleneck, and local elasticity. Finally, we discuss how neurashed can guide the development of deep learning theories.

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
Science China Information Sciences
Science China Information Sciences COMPUTER SCIENCE, INFORMATION SYSTEMS-
CiteScore
12.60
自引率
5.70%
发文量
224
审稿时长
8.3 months
期刊介绍: Science China Information Sciences is a dedicated journal that showcases high-quality, original research across various domains of information sciences. It encompasses Computer Science & Technologies, Control Science & Engineering, Information & Communication Engineering, Microelectronics & Solid-State Electronics, and Quantum Information, providing a platform for the dissemination of significant contributions in these fields.
×
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