The Global Landscape of Neural Networks: An Overview

被引:59
|
作者
Sun, Ruoyu [1 ,2 ,3 ,4 ]
Li, Dawei [1 ]
Liang, Shiyu [5 ]
Ding, Tian [6 ]
Srikant, Rayadurgam [2 ,3 ]
机构
[1] Univ Illinois Urbana Champaign UIUC, Dept Ind & Enterprise Syst Engn, Champaign, IL 61820 USA
[2] Univ Illinois Urbana Champaign UIUC, Coordinated Sci Lab, Champaign, IL 61820 USA
[3] Univ Illinois Urbana Champaign UIUC, Dept Elect & Comp Engn, Champaign, IL 61820 USA
[4] Stanford Univ, Stanford, CA 94305 USA
[5] Univ Illinois Urbana Champaign UIUC, Champaign, IL USA
[6] Chinese Univ Hong Kong, Hong Kong, Peoples R China
关键词
Optimization; Signal processing algorithms; Training; Biological neural networks; Convergence; Machine learning;
D O I
10.1109/MSP.2020.3004124
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
One of the major concerns for neural network training is that the nonconvexity of the associated loss functions may cause a bad landscape. The recent success of neural networks suggests that their loss landscape is not too bad, but what specific results do we know about the landscape? In this article, we review recent findings and results on the global landscape of neural networks.
引用
收藏
页码:95 / 108
页数:14
相关论文
共 50 条
  • [41] NEURAL NETWORKS AND OPERATIONS-RESEARCH - AN OVERVIEW
    BURKE, LI
    IGNIZIO, JP
    COMPUTERS & OPERATIONS RESEARCH, 1992, 19 (3-4) : 179 - 189
  • [42] AN OVERVIEW OF ARTIFICIAL NEURAL NETWORKS APPLICATION IN TRANSPORTATION
    Zenina, Nadezda
    Merkuryev, Yuri
    MENDEL 2008, 2008, : 12 - 16
  • [43] A brief overview and introduction to artificial neural networks
    Buscema, M
    SUBSTANCE USE & MISUSE, 2002, 37 (8-10) : 1093 - 1148
  • [44] Overview of RFID Applications Utilizing Neural Networks
    Durtschi, Barrett D.
    Chrysler, Andrew M.
    IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION, 2024, 8 : 801 - 810
  • [45] Overview of Visualization Methods for Artificial Neural Networks
    Matveev, S. A.
    Oseledets, I., V
    Ponomarev, E. S.
    Chertkov, A., V
    COMPUTATIONAL MATHEMATICS AND MATHEMATICAL PHYSICS, 2021, 61 (05) : 887 - 899
  • [46] Overview of the Research Status on Artificial Neural Networks
    Wang Xin-gang
    PROCEEDINGS OF THE 2ND INTERNATIONAL FORUM ON MANAGEMENT, EDUCATION AND INFORMATION TECHNOLOGY APPLICATION (IFMEITA 2017), 2017, 130 : 351 - 356
  • [47] Hardware Compilation of Deep Neural Networks: An Overview
    Zhao, Ruizhe
    Liu, Shuanglong
    Ng, Ho-Cheung
    Wang, Erwei
    Davis, James J.
    Niu, Xinyu
    Wang, Xiwei
    Shi, Huifeng
    Constantinides, George A.
    Cheung, Peter Y. K.
    Luk, Wayne
    2018 IEEE 29TH INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS (ASAP), 2018, : 120 - 127
  • [48] Deep Neural Networks in Machine Translation: An Overview
    Zhang, Jiajun
    Zong, Chengqing
    IEEE INTELLIGENT SYSTEMS, 2015, 30 (05) : 16 - 25
  • [49] Overview of the applications of neural networks in process engineering
    Mirzai, A.R.
    Leigh, J.R.
    Computing and Control Engineering Journal, 1992, 3 (03): : 105 - 108
  • [50] Overview of Visualization Methods for Artificial Neural Networks
    S. A. Matveev
    I. V. Oseledets
    E. S. Ponomarev
    A. V. Chertkov
    Computational Mathematics and Mathematical Physics, 2021, 61 : 887 - 899