咨询与建议

限定检索结果

文献类型

  • 37 篇 会议
  • 22 篇 期刊文献

馆藏范围

  • 59 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 59 篇 工学
    • 50 篇 计算机科学与技术...
    • 26 篇 电气工程
    • 10 篇 软件工程
    • 7 篇 信息与通信工程
    • 3 篇 生物医学工程(可授...
    • 2 篇 仪器科学与技术
    • 2 篇 电子科学与技术(可...
    • 2 篇 控制科学与工程
    • 1 篇 机械工程
    • 1 篇 测绘科学与技术
    • 1 篇 交通运输工程
    • 1 篇 航空宇航科学与技...
    • 1 篇 网络空间安全
  • 14 篇 医学
    • 11 篇 临床医学
    • 2 篇 基础医学(可授医学...
    • 2 篇 特种医学
  • 9 篇 理学
    • 7 篇 物理学
    • 1 篇 化学
    • 1 篇 地球物理学
    • 1 篇 生物学
  • 2 篇 管理学
    • 2 篇 管理科学与工程(可...

主题

  • 59 篇 neural network q...
  • 8 篇 deep learning
  • 6 篇 model compressio...
  • 5 篇 edge computing
  • 4 篇 speaker verifica...
  • 4 篇 neural network a...
  • 4 篇 quantization (si...
  • 3 篇 mixed precision ...
  • 3 篇 object detection
  • 3 篇 computational ef...
  • 3 篇 machine learning
  • 3 篇 hardware acceler...
  • 3 篇 training
  • 2 篇 neural network r...
  • 2 篇 image segmentati...
  • 2 篇 neural network c...
  • 2 篇 error resilience
  • 2 篇 mixed precision
  • 2 篇 mixed-precision ...
  • 2 篇 integer-only

机构

  • 2 篇 univ calif san d...
  • 2 篇 tsinghua univ ct...
  • 2 篇 natl taiwan univ...
  • 2 篇 chinese univ hon...
  • 2 篇 mcgill univ sch ...
  • 2 篇 univ calif santa...
  • 2 篇 univ illinois el...
  • 2 篇 aristotle univ t...
  • 2 篇 city univ hong k...
  • 2 篇 xiamen univ sch ...
  • 2 篇 beihang univ sch...
  • 2 篇 univ sci & techn...
  • 1 篇 cea tech syst & ...
  • 1 篇 clemson univ dep...
  • 1 篇 univ kairouan fa...
  • 1 篇 shanghai jiao to...
  • 1 篇 tsinghua univ be...
  • 1 篇 beijing inst tec...
  • 1 篇 fraunhofer heinr...
  • 1 篇 univ sci & techn...

作者

  • 5 篇 qian yanmin
  • 4 篇 wang haoyu
  • 4 篇 liu bei
  • 3 篇 wu yifei
  • 2 篇 wu shangyu
  • 2 篇 pleros n.
  • 2 篇 jeong hyunmin
  • 2 篇 tefas a.
  • 2 篇 liu xunying
  • 2 篇 zhang rongzhao
  • 2 篇 moralis-pegios m...
  • 2 篇 kang yi
  • 2 篇 passalis n.
  • 2 篇 kang wang
  • 2 篇 oikonomou a.
  • 2 篇 xie yuan
  • 2 篇 kuo tei-wei
  • 2 篇 deng lei
  • 2 篇 bai jinyu
  • 2 篇 xue chun jason

语言

  • 59 篇 英文
检索条件"主题词=neural network quantization"
59 条 记 录,以下是1-10 订阅
排序:
Towards Lightweight Speaker Verification via Adaptive neural network quantization
收藏 引用
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2024年 32卷 3771-3784页
作者: Liu, Bei Wang, Haoyu Qian, Yanmin Shanghai Jiao Tong Univ AI Inst Dept Comp Sci & Engn Auditory Cognit & Computat Acoust Lab Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai 200240 Peoples R China
Modern speaker verification (SV) systems typically demand expensive storage and computing resources, thereby hindering their deployment on mobile devices. In this paper, we explore adaptive neural network quantization... 详细信息
来源: 评论
EfficientQ: An efficient and accurate post-training neural network quantization method for medical image segmentation
收藏 引用
MEDICAL IMAGE ANALYSIS 2024年 97卷 103277页
作者: Zhang, Rongzhao Chung, Albert C. S. Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China
Model quantization is a promising technique that can simultaneously compress and accelerate a deep neural network by limiting its computation bit-width, which plays a crucial role in the fast-growing AI industry. Desp... 详细信息
来源: 评论
FedQNN: A Computation-Communication-Efficient Federated Learning Framework for IoT With Low-Bitwidth neural network quantization
收藏 引用
IEEE INTERNET OF THINGS JOURNAL 2023年 第3期10卷 2494-2507页
作者: Ji, Yu Chen, Lan Chinese Acad Sci Inst Microelect Beijing 100029 Peoples R China Beijing Municipal Commiss Sci & Technol Beijing Key Lab Three Dimens & Nanometer Integrate Beijing 100029 Peoples R China
Federated learning (FL) allows participants to train deep learning models collaboratively without disclosing their data to the server or any other participants, providing excellent value in the field of privacy-sensit... 详细信息
来源: 评论
LOW BIT neural network quantization FOR SPEAKER VERIFICATION
LOW BIT NEURAL NETWORK QUANTIZATION FOR SPEAKER VERIFICATION
收藏 引用
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Wang, Haoyu Liu, Bei Wu, Yifei Chen, Zhengyang Qian, Yanmin Shanghai Jiao Tong Univ AI Inst Dept Comp Sci & Engn MoE Key Lab Artificial IntelligenceX LANCE Lab Shanghai Peoples R China
With the continuous development of deep neural networks (DNN) in recent years, the performance of speaker verification systems has been significantly improved with the application of Deeper ResNet architectures. Howev... 详细信息
来源: 评论
Adaptive neural network quantization for Lightweight Speaker Verification  24
Adaptive Neural Network Quantization for Lightweight Speaker...
收藏 引用
Interspeech Conference
作者: Wang, Haoyu Liu, Bei Wu, Yifei Qian, Yanmin Shanghai Jiao Tong Univ MoE Key Lab Artificial Intelligence AI Inst X LANCE LabDept Comp Sci & Engn Shanghai Peoples R China
Recently, speaker verification systems benefit from deep neural networks and the size of speaker embedding encoder increases with these sophisticated architectures. Nevertheless, mobile devices have inadequate memory ... 详细信息
来源: 评论
CEG4N: Counter-Example Guided neural network quantization Refinement  5th
CEG4N: Counter-Example Guided Neural Network Quantization Re...
收藏 引用
5th International Workshop on Formal Methods for ML-Enabled Autonomous Systems (FoMLAS)
作者: Matos Jr, Joao Batista P. Bessa, Iury Manino, Edoardo Song, Xidan Cordeiro, Lucas C. Univ Fed Amazonas Manaus Amazonas Brazil Univeristy Manchester Machester England
neural networks are essential components of learning-based software systems. However, deploying neural networks in low-resource domains is challenging because of their high computing, memory, and power requirements. F... 详细信息
来源: 评论
A 4-bit Integer-Only neural network quantization Method Based on Shift Batch Normalization
A 4-bit Integer-Only Neural Network Quantization Method Base...
收藏 引用
IEEE International Symposium on Circuits and Systems (ISCAS)
作者: Guo, Qingyu Cui, Xiaoxin Zhang, Jian Zhang, Aifei Guo, Xinjie Wang, Yuan Peking Univ Sch Integrated Circuits Key Lab Microelect Devices & Circuits MoE Beijing 100871 Peoples R China Beijing Zhicun WITIN Technol Corp Ltd Beijing 100191 Peoples R China Peking Univ Beijing Lab Future IC Technol & Sci Beijing 100871 Peoples R China
neural networks are powerful, but at the cost of huge amounts of computation. Deploying neural networks on edge devices is especially challenging. quantization is a possible solution to alleviate the huge cost, while ... 详细信息
来源: 评论
Auto-tuning neural network quantization Framework for Collaborative Inference Between the Cloud and Edge  27th
Auto-tuning Neural Network Quantization Framework for Collab...
收藏 引用
27th International Conference on Artificial neural networks (ICANN)
作者: Li, Guangli Liu, Lei Wang, Xueying Dong, Xiao Zhao, Peng Feng, Xiaobing Chinese Acad Sci Inst Comp Technol State Key Lab Comp Architecture Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China
Recently, deep neural networks (DNNs) have been widely applied in mobile intelligent applications. The inference for the DNNs is usually performed in the cloud. However, it leads to a large overhead of transmitting da... 详细信息
来源: 评论
LIGHT-WEIGHT VISUALVOICE: neural network quantization ON AUDIO VISUAL SPEECH SEPARATION
LIGHT-WEIGHT VISUALVOICE: NEURAL NETWORK QUANTIZATION ON AUD...
收藏 引用
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Wu, Yifei Li, Chenda Qian, Yanmin Shanghai Jiao Tong Univ Dept Comp Sci & Engn X LANCE Lab MoE Key Lab Artificial IntelligenceAI Inst Shanghai Peoples R China
As multi-modal systems show superior performance on more tasks, the huge amount of computational resources they need becomes one of the critical problems to be solved. In this work, we explore neural network quantizat... 详细信息
来源: 评论
MedQ: Lossless ultra-low-bit neural network quantization for medical image segmentation
收藏 引用
MEDICAL IMAGE ANALYSIS 2021年 73卷 102200-102200页
作者: Zhang, Rongzhao Chung, Albert C. S. Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Lo Kwee Seong Med Image Anal Lab Hong Kong Peoples R China
Implementing deep convolutional neural networks (CNNs) with boolean arithmetic is ideal for eliminating the notoriously high computational expense of deep learning models. However, although lossless model compression ... 详细信息
来源: 评论