基于dnn的局部多核学习的高效经验求解器

Ziming Zhang
{"title":"基于dnn的局部多核学习的高效经验求解器","authors":"Ziming Zhang","doi":"10.1109/ICPR48806.2021.9411974","DOIUrl":null,"url":null,"abstract":"In this paper we propose solving localized multiple kernel learning (LMKL) using LMKL-Net, a feedforward deep neural network (DNN). In contrast to previous works, as a learning principle we propose parameterizing the gating function for learning kernel combination weights and the multiclass classifier using an attentional network (AN) and a multilayer perceptron (MLP), respectively. Such interpretability helps us better understand how the network solves the problem. Thanks to stochastic gradient descent (SGD), our approach has linear computational complexity in training. Empirically on benchmark datasets we demonstrate that with comparable or better accuracy than the state-of-the-art, our LMKL-Net can be trained about two orders of magnitude faster with about two orders of magnitude smaller memory footprint for large-scale learning.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"71 3 1","pages":"647-654"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"An Efficient Empirical Solver for Localized Multiple Kernel Learning via DNNs\",\"authors\":\"Ziming Zhang\",\"doi\":\"10.1109/ICPR48806.2021.9411974\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper we propose solving localized multiple kernel learning (LMKL) using LMKL-Net, a feedforward deep neural network (DNN). In contrast to previous works, as a learning principle we propose parameterizing the gating function for learning kernel combination weights and the multiclass classifier using an attentional network (AN) and a multilayer perceptron (MLP), respectively. Such interpretability helps us better understand how the network solves the problem. Thanks to stochastic gradient descent (SGD), our approach has linear computational complexity in training. Empirically on benchmark datasets we demonstrate that with comparable or better accuracy than the state-of-the-art, our LMKL-Net can be trained about two orders of magnitude faster with about two orders of magnitude smaller memory footprint for large-scale learning.\",\"PeriodicalId\":6783,\"journal\":{\"name\":\"2020 25th International Conference on Pattern Recognition (ICPR)\",\"volume\":\"71 3 1\",\"pages\":\"647-654\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-01-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 25th International Conference on Pattern Recognition (ICPR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICPR48806.2021.9411974\",\"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 25th International Conference on Pattern Recognition (ICPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICPR48806.2021.9411974","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

本文提出利用前馈深度神经网络LMKL- net解决局部多核学习(LMKL)问题。与之前的研究相反,作为一种学习原理,我们提出了参数化门控函数来学习核组合权值,并分别使用注意网络(an)和多层感知器(MLP)来学习多类分类器。这种可解释性有助于我们更好地理解网络是如何解决问题的。由于随机梯度下降(SGD),我们的方法在训练中具有线性计算复杂度。在基准数据集的经验上,我们证明了与最先进的技术相比,我们的LMKL-Net可以以大约两个数量级的速度训练,并且在大规模学习中可以减少大约两个数量级的内存占用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
An Efficient Empirical Solver for Localized Multiple Kernel Learning via DNNs
In this paper we propose solving localized multiple kernel learning (LMKL) using LMKL-Net, a feedforward deep neural network (DNN). In contrast to previous works, as a learning principle we propose parameterizing the gating function for learning kernel combination weights and the multiclass classifier using an attentional network (AN) and a multilayer perceptron (MLP), respectively. Such interpretability helps us better understand how the network solves the problem. Thanks to stochastic gradient descent (SGD), our approach has linear computational complexity in training. Empirically on benchmark datasets we demonstrate that with comparable or better accuracy than the state-of-the-art, our LMKL-Net can be trained about two orders of magnitude faster with about two orders of magnitude smaller memory footprint for large-scale learning.
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
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