中国科学院计算技术研究所机构知识库

浏览/检索结果: 共8条，第1-8条

帮助

已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序WOS被引频次升序WOS被引频次降序提交时间升序提交时间降序期刊影响因子升序期刊影响因子降序题名升序题名降序发表日期升序发表日期降序
	BIRD plus : Design of a Lightweight Communication Compressor for Resource-Constrained Distribution Learning Platforms 期刊论文 IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2024, 卷号: 35, 期号: 11, 页码: 2193-2207 作者:  Wu, Donglei;  Yang, Weihao;  Zou, Xiangyu;  Feng, Hao;  Tao, Dingwen;  Li, Shiyi;  Xia, Wen;  Fang, Binxing 收藏  |  浏览/下载：1/0  |  提交时间：2024/12/06 Indexes  Costs  Computational modeling  Distance learning  Computer aided instruction  Training  Tensors  Distributed learning  communication compression  random sampling  neural network
	DPQ: dynamic pseudo-mean mixed-precision quantization for pruned neural network 期刊论文 MACHINE LEARNING, 2024, 页码: 14 作者:  Pei, Songwen;  Wang, Jiyao;  Zhang, Bingxue;  Qin, Wei;  Xue, Hai;  Ye, Xiaochun;  Chen, Mingsong 收藏  |  浏览/下载：14/0  |  提交时间：2024/05/20 Big data  Compression  Deep learning  Pseudo-mean mixed-precision quantization  Pruned neural network
	Fpar: filter pruning via attention and rank enhancement for deep convolutional neural networks acceleration 期刊论文 INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024, 页码: 13 作者:  Chen, Yanming;  Wu, Gang;  Shuai, Mingrui;  Lou, Shubin;  Zhang, Yiwen;  An, Zhulin 收藏  |  浏览/下载：17/0  |  提交时间：2024/05/20 Neural network  Model compression  Filter pruning  Attention  Rank enhancement  CNNs
	Accelerating deep neural network filter pruning with mask-aware convolutional computations on modern CPUs 期刊论文 NEUROCOMPUTING, 2022, 卷号: 505, 页码: 375-387 作者:  Ma, Xiu;  Li, Guangli;  Liu, Lei;  Liu, Huaxiao;  Wang, Xueying 收藏  |  浏览/下载：19/0  |  提交时间：2023/07/12 Deep learning systems  Neural network compression  Filter pruning
	Optimizing deep neural networks on intelligent edge accelerators via flexible-rate filter pruning 期刊论文 JOURNAL OF SYSTEMS ARCHITECTURE, 2022, 卷号: 124, 页码: 11 作者:  Li, Guangli;  Ma, Xiu;  Wang, Xueying;  Yue, Hengshan;  Li, Jiansong;  Liu, Lei;  Feng, Xiaobing;  Xue, Jingling 收藏  |  浏览/下载：34/0  |  提交时间：2022/12/07 Edge intelligence  Deep learning  Neural network compression
	Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization 期刊论文 IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 15 作者:  Deng, Lei;  Wu, Yujie;  Hu, Yifan;  Liang, Ling;  Li, Guoqi;  Hu, Xing;  Ding, Yufei;  Li, Peng;  Xie, Yuan 收藏  |  浏览/下载：37/0  |  提交时间：2022/06/21 Neurons  Computational modeling  Quantization (signal)  Optimization  Encoding  Task analysis  Synapses  Activity regularization  alternating direction method of multiplier (ADMM)  connection pruning  spiking neural network (SNN) compression  weight quantization
	A deep neural network compression algorithm based on knowledge transfer for edge devices 期刊论文 COMPUTER COMMUNICATIONS, 2020, 卷号: 163, 页码: 186-194 作者:  Chen, Yanming;  Li, Chao;  Gong, Luqi;  Wen, Xiang;  Zhang, Yiwen;  Shi, Weisong 收藏  |  浏览/下载：346/0  |  提交时间：2020/12/10 Edge device  Deep learning  Neural network compression  Knowledge transfer
	Optimization feature compression and FNN realization 期刊论文 INTELLIGENT CONTROL AND AUTOMATION, 2006, 卷号: 344, 页码: 951-956 作者:  Ding, Shifei;  Wang, Yuncheng;  Shi, Zhongzhi;  Jin, Fengxiang 收藏  |  浏览/下载：44/0  |  提交时间：2019/12/16 pattern recognition  optimization feature compression  entropy density function (EDF)  representation entropy (RE)  feedforward neural network (FNN)