发布求助
文献互助 智能选刊 最新文献

Mach. Learn. Sci. Technol.最新文献

筛选
英文 中文
A Free-Energy Principle for Representation Learning 表征学习的自由能原理
Mach. Learn. Sci. Technol. Pub Date : 2020-02-27 DOI: 10.1088/2632-2153/ABF984
Yansong Gao, P. Chaudhari
{"title":"A Free-Energy Principle for Representation Learning","authors":"Yansong Gao, P. Chaudhari","doi":"10.1088/2632-2153/ABF984","DOIUrl":"https://doi.org/10.1088/2632-2153/ABF984","url":null,"abstract":"This paper employs a formal connection of machine learning with thermodynamics to characterize the quality of learnt representations for transfer learning. We discuss how information-theoretic functional such as rate, distortion and classification loss of a model lie on a convex, so-called equilibrium surface.We prescribe dynamical processes to traverse this surface under constraints, e.g., an iso-classification process that trades off rate and distortion to keep the classification loss unchanged. We demonstrate how this process can be used for transferring representations from a source dataset to a target dataset while keeping the classification loss constant. Experimental validation of the theoretical results is provided on standard image-classification datasets.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"36 1","pages":"45004"},"PeriodicalIF":0.0,"publicationDate":"2020-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90874562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
Large deviations for the perceptron model and consequences for active learning 感知器模型的大偏差和主动学习的后果
Mach. Learn. Sci. Technol. Pub Date : 2019-12-09 DOI: 10.1088/2632-2153/ABFBBB
Hugo Cui, Luca Saglietti, Lenka Zdeborov'a
{"title":"Large deviations for the perceptron model and consequences for active learning","authors":"Hugo Cui, Luca Saglietti, Lenka Zdeborov'a","doi":"10.1088/2632-2153/ABFBBB","DOIUrl":"https://doi.org/10.1088/2632-2153/ABFBBB","url":null,"abstract":"Active learning is a branch of machine learning that deals with problems where unlabeled data is abundant yet obtaining labels is expensive. The learning algorithm has the possibility of querying a limited number of samples to obtain the corresponding labels, subsequently used for supervised learning. In this work, we consider the task of choosing the subset of samples to be labeled from a fixed finite pool of samples. We assume the pool of samples to be a random matrix and the ground truth labels to be generated by a single-layer teacher random neural network. We employ replica methods to analyze the large deviations for the accuracy achieved after supervised learning on a subset of the original pool. These large deviations then provide optimal achievable performance boundaries for any active learning algorithm. We show that the optimal learning performance can be efficiently approached by simple message-passing active learning algorithms. We also provide a comparison with the performance of some other popular active learning strategies.","PeriodicalId":18148,"journal":{"name":"Mach. Learn. Sci. Technol.","volume":"66 1","pages":"45001"},"PeriodicalIF":0.0,"publicationDate":"2019-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74472820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
首页 上一页
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
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
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