Automated Multi-Stage Compression of Neural Networks

被引:29
|
作者
Gusak, Julia [1 ]
Kholiavchenko, Maksym [2 ]
Ponomarev, Evgeny [1 ]
Markeeva, Larisa [1 ]
Blagoveschensky, Philip [1 ,3 ]
Cichocki, Andrzej [1 ]
Oseledets, Ivan [1 ]
机构
[1] Skolkovo Inst Sci & Technol, Moscow, Russia
[2] Innopolis Univ, Innopolis, Russia
[3] Huawei Noahs Ark Lab, Hong Kong, Peoples R China
基金
俄罗斯科学基金会;
关键词
D O I
10.1109/ICCVW.2019.00306
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Low-rank tensor approximations are very promising for compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our approach improves the compression rate while maintaining the accuracy for a variety of tasks.
引用
收藏
页码:2501 / 2508
页数:8
相关论文
共 50 条
  • [1] Convolutional Neural Networks for Multi-Stage Semiconductor Processes
    Wu, Xiaofei
    Chen, Junghui
    Xie, Lei
    Lee, Yishan
    Chen, Chun-, I
    [J]. JOURNAL OF CHEMICAL ENGINEERING OF JAPAN, 2021, 54 (08) : 449 - 455
  • [2] Microcalcification detection using multi-stage of neural networks
    Shin, JW
    Lee, SS
    Yoon, S
    Park, DS
    [J]. 7TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL IV, PROCEEDINGS: IMAGE, ACOUSTIC, SPEECH AND SIGNAL PROCESSING, 2003, : 229 - 234
  • [3] Multi-stage neural networks for channel assignment in cellular radio networks
    Lee, HS
    Lee, DW
    Lee, J
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 2, 2004, 3174 : 287 - 292
  • [4] Reconfigurable multi-stage neural networks in monitoring industrial machines
    Marzi, H
    [J]. SMCia/05: Proceedings of the 2005 IEEE Mid-Summer Workshop on Soft Computing in Industrial Applications, 2005, : 142 - 147
  • [5] Portfolio optimization for multi-stage capital investment with neural networks
    Zhang, YL
    Hua, Y
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 2, 2004, 3174 : 982 - 987
  • [6] Multi-stage neural networks: Function approximator of machine precision
    Wang, Yongji
    Lai, Ching-Yao
    [J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2024, 504
  • [7] Ensemble of multi-stage deep convolutional neural networks for automated grading of diabetic retinopathy using image patches
    Deepa, V.
    Kumar, C. Sathish
    Cherian, Thomas
    [J]. JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2022, 34 (08) : 6255 - 6265
  • [8] Image Classification Using Convolutional Neural Networks With Multi-stage Feature
    Yim, Junho
    Ju, Jeongwoo
    Jung, Heechul
    Kim, Junmo
    [J]. ROBOT INTELLIGENCE TECHNOLOGY ANDAPPLICATIONS 3, 2015, 345 : 587 - 594
  • [9] Facial Age Estimation Using Multi-Stage Deep Neural Networks
    Bekhouche, Salah Eddine
    Benlamoudi, Azeddine
    Dornaika, Fadi
    Telli, Hichem
    Bounab, Yazid
    [J]. ELECTRONICS, 2024, 13 (16)
  • [10] Multi-stage neural networks with application to motion planning of a mechanical snake
    Fidan, B
    Sezert, E
    Akar, M
    [J]. PROCEEDINGS OF THE 2003 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2003, : 1278 - 1283