机构

• 计算技术研究所 [11]
• 自动化研究所 [7]
• 长春光学精密机械与物... [2]
• 地理科学与资源研究所 [1]
• 数学与系统科学研究院 [1]
• 沈阳自动化研究所 [1]
• 更多

采集方式

• OAI收割 [23]

内容类型

• 期刊论文 [17]
• 会议论文 [5]
• 学位论文 [1]

发表日期

• 2024 [4]
• 2023 [1]
• 2022 [4]
• 2021 [2]
• 2020 [3]
• 2018 [2]
• 更多

学科主题

筛选

浏览/检索结果: 共23条，第1-10条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 An adaptive joint optimization framework for pruning and quantization 期刊论文  OAI收割 INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024, 页码: 17 作者:  Li, Xiaohai;  Yang, Xiaodong;  Zhang, Yingwei;  Yang, Jianrong;  Chen, Yiqiang   |  收藏  |  浏览/下载：6/0  |  提交时间：2024/12/06 Model compression  Network pruning  Quantization  Mutual learning  Multi-teacher knowledge distillation   Per-Packet Traffic Measurement in Storage, Computation and Bandwidth Limited Data Plane 期刊论文  OAI收割 IEEE-ACM TRANSACTIONS ON NETWORKING, 2024, 页码: 13 作者:  Cong, Yinchuan;  Xie, Kun;  Wen, Jigang;  Zhang, Jiwei;  Yin, Yansong   |  收藏  |  浏览/下载：4/0  |  提交时间：2024/12/06 Sequence of packet lengths and arrival times (SPLT)  data plane  packet level measurement  in-network calculation  quantization   An Automatic Neural Network Architecture-and-Quantization Joint Optimization Framework for Efficient Model Inference 期刊论文  OAI收割 IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2024, 卷号: 43, 期号: 5, 页码: 1497-1510 作者:  Liu, Lian;  Wang, Ying;  Zhao, Xiandong;  Chen, Weiwei;  Li, Huawei   |  收藏  |  浏览/下载：5/0  |  提交时间：2024/12/06 Optimization  Quantization (signal)  Computer architecture  Training  Computational modeling  Integrated circuit modeling  Convergence  Automatic joint optimization  efficient model inference  network quantization  neural architecture search (NAS)   DPQ: dynamic pseudo-mean mixed-precision quantization for pruned neural network 期刊论文  OAI收割 MACHINE LEARNING, 2024, 页码: 14 作者:  Pei, Songwen;  Wang, Jiyao;  Zhang, Bingxue;  Qin, Wei;  Xue, Hai   |  收藏  |  浏览/下载：19/0  |  提交时间：2024/05/20 Big data  Compression  Deep learning  Pseudo-mean mixed-precision quantization  Pruned neural network   PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators 期刊论文  OAI收割 IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 4472-4485 作者:  Cong, Runmin;  Yang, Wenyu;  Zhang, Wei;  Li, Chongyi;  Guo, Chun-Le   |  收藏  |  浏览/下载：20/0  |  提交时间：2023/12/04 Underwater image enhancement  generative adversarial network  physical model  degradation quantization   Towards efficient full 8-bit integer DNN online training on resource-limited devices without batch normalization 期刊论文  OAI收割 NEUROCOMPUTING, 2022, 卷号: 511, 页码: 175-186 作者:  Yang, Yukuan;  Chi, Xiaowei;  Deng, Lei;  Yan, Tianyi;  Gao, Feng   |  收藏  |  浏览/下载：48/0  |  提交时间：2022/11/21 Full 8-bit quantization  Network without batch normalization  Small batch  Online training  Resource-limited devices   An Automated Quantization Framework for High-Utilization RRAM-Based PIM 期刊论文  OAI收割 IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2022, 卷号: 41, 期号: 3, 页码: 583-596 作者:  Li, Bing;  Qu, Songyun;  Wang, Ying   |  收藏  |  浏览/下载：45/0  |  提交时间：2022/12/07 Quantization (signal)  Neural networks  Computational modeling  Data models  Hardware  Resource management  Arrays  AutoML  neural network  processing-in-memory (PIM)  quantization  resistive memory (RRAM)   Rethinking the Importance of Quantization Bias, Toward Full Low-Bit Training 期刊论文  OAI收割 IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 7006-7019 作者:  Liu, Chang;  Zhang, Xishan;  Zhang, Rui;  Li, Ling;  Zhou, Shiyi   |  收藏  |  浏览/下载：14/0  |  提交时间：2023/07/12 Neural network acceleration  low precision training  quantization   LINAC: A Spatially Linear Accelerator for Convolutional Neural Networks 期刊论文  OAI收割 IEEE COMPUTER ARCHITECTURE LETTERS, 2022, 卷号: 21, 期号: 1, 页码: 29-32 作者:  Xiao, Hang;  Xu, Haobo;  Wang, Ying;  Wang, Yujie;  Han, Yinhe   |  收藏  |  浏览/下载：51/0  |  提交时间：2022/12/07 Linear particle accelerator  Correlation  Kernel  Convolution  Linear regression  System-on-chip  Quantization (signal)  Neural network  acceleration  convolution  linear regression  bit-sparsity   Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization 期刊论文  OAI收割 IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 15 作者:  Deng, Lei;  Wu, Yujie;  Hu, Yifan;  Liang, Ling;  Li, Guoqi   |  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