Neural network relief: a pruning algorithm based on neural activity

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Machine Learning Pub Date : 2024-03-05 DOI:10.1007/s10994-024-06516-z
{"title":"Neural network relief: a pruning algorithm based on neural activity","authors":"","doi":"10.1007/s10994-024-06516-z","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>Current deep neural networks (DNNs) are overparameterized and use most of their neuronal connections during inference for each task. The human brain, however, developed specialized regions for different tasks and performs inference with a small fraction of its neuronal connections. We propose an iterative pruning strategy introducing a simple importance-score metric that deactivates unimportant connections, tackling overparameterization in DNNs and modulating the firing patterns. The aim is to find the smallest number of connections that is still capable of solving a given task with comparable accuracy, i.e. a simpler subnetwork. We achieve comparable performance for LeNet architectures on MNIST, and significantly higher parameter compression than state-of-the-art algorithms for VGG and ResNet architectures on CIFAR-10/100 and Tiny-ImageNet. Our approach also performs well for the two different optimizers considered—Adam and SGD. The algorithm is not designed to minimize FLOPs when considering current hardware and software implementations, although it performs reasonably when compared to the state of the art.</p>","PeriodicalId":49900,"journal":{"name":"Machine Learning","volume":"26 1","pages":""},"PeriodicalIF":4.3000,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Machine Learning","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10994-024-06516-z","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Current deep neural networks (DNNs) are overparameterized and use most of their neuronal connections during inference for each task. The human brain, however, developed specialized regions for different tasks and performs inference with a small fraction of its neuronal connections. We propose an iterative pruning strategy introducing a simple importance-score metric that deactivates unimportant connections, tackling overparameterization in DNNs and modulating the firing patterns. The aim is to find the smallest number of connections that is still capable of solving a given task with comparable accuracy, i.e. a simpler subnetwork. We achieve comparable performance for LeNet architectures on MNIST, and significantly higher parameter compression than state-of-the-art algorithms for VGG and ResNet architectures on CIFAR-10/100 and Tiny-ImageNet. Our approach also performs well for the two different optimizers considered—Adam and SGD. The algorithm is not designed to minimize FLOPs when considering current hardware and software implementations, although it performs reasonably when compared to the state of the art.

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
神经网络救济:基于神经活动的剪枝算法
摘要 当前的深度神经网络(DNN)参数过高,在推理每个任务时都会使用大部分神经元连接。然而,人类大脑为不同的任务开发了专门的区域,并使用其神经元连接的一小部分执行推理。我们提出了一种迭代剪枝策略,引入了一个简单的重要性分数指标,停用不重要的连接,解决 DNN 中的过度参数化问题,并调节发射模式。这样做的目的是找到最小数量的连接,这些连接仍能以相当的精度解决给定任务,即一个更简单的子网络。我们在 MNIST 上实现了与 LeNet 架构相当的性能,在 CIFAR-10/100 和 Tiny-ImageNet 上实现了比 VGG 和 ResNet 架构先进算法更高的参数压缩率。我们的方法在两种不同的优化器--Adam 和 SGD 中也表现出色。考虑到当前的硬件和软件实现,该算法并不是为了最小化 FLOPs 而设计的,不过与最先进的算法相比,它的表现还算合理。
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
Machine Learning
Machine Learning 工程技术-计算机:人工智能
CiteScore
11.00
自引率
2.70%
发文量
162
审稿时长
3 months
期刊介绍: Machine Learning serves as a global platform dedicated to computational approaches in learning. The journal reports substantial findings on diverse learning methods applied to various problems, offering support through empirical studies, theoretical analysis, or connections to psychological phenomena. It demonstrates the application of learning methods to solve significant problems and aims to enhance the conduct of machine learning research with a focus on verifiable and replicable evidence in published papers.
期刊最新文献
On metafeatures’ ability of implicit concept identification Persistent Laplacian-enhanced algorithm for scarcely labeled data classification Towards a foundation large events model for soccer Conformal prediction for regression models with asymmetrically distributed errors: application to aircraft navigation during landing maneuver In-game soccer outcome prediction with offline reinforcement learning
×
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