Visualization in Deep Neural Network Training

被引：0
|
作者：
Kollias, Stefanos [1 ]
机构：
[1] Natl Tech Univ Athens, Sch Elect & Comp Engn, Zografos 15780, Greece
来源：
INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS | 2022年 / 31卷 / 03期
关键词：
Deep neural networks; learning; latent variables; clustering; visualization;
D O I：
10.1142/S0218213022410044
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Visualizing the decision making procedure of a deep neural network is one of the main challenges towards transparent and trustworthy artificial intelligence. This paper presents an approach which extracts latent variables from a trained network and, through clustering, constructs a set of anchors that represent the network's data driven knowledge. This set is then used to inform users about the features that create network's decision.
引用
收藏
页数：6
相关论文
共 50 条
  • [1] DNNViz: Training Evolution Visualization for Deep Neural Networks
    Clavien, Gil
    Alberti, Michele
    Pondenkandath, Vinaychandran
    Ingold, Rolf
    Liwicki, Marcus
    [J]. 2019 6TH SWISS CONFERENCE ON DATA SCIENCE (SDS), 2019, : 19 - 24
  • [2] Malware detection employed by visualization and deep neural network
    Pinhero, Anson
    Anupama, M. L.
    Vinod, P.
    Visaggio, C. A.
    Aneesh, N.
    Abhijith, S.
    AnanthaKrishnan, S.
    [J]. COMPUTERS & SECURITY, 2021, 105
  • [3] RazorNet: Adversarial Training and Noise Training on a Deep Neural Network Fooled by a Shallow Neural Network
    Taheri, Shayan
    Salem, Milad
    Yuan, Jiann-Shiun
    [J]. BIG DATA AND COGNITIVE COMPUTING, 2019, 3 (03) : 1 - 17
  • [4] Memory Efficient Deep Neural Network Training
    Shilova, Alena
    [J]. EURO-PAR 2021: PARALLEL PROCESSING WORKSHOPS, 2022, 13098 : 515 - 519
  • [5] Benchmarking and Analyzing Deep Neural Network Training
    Zhu, Hongyu
    Akrout, Mohamed
    Zheng, Bojian
    Pelegris, Andrew
    Jayarajan, Anand
    Phanishayee, Amar
    Schroeder, Bianca
    Pekhimenko, Gennady
    [J]. 2018 IEEE INTERNATIONAL SYMPOSIUM ON WORKLOAD CHARACTERIZATION (IISWC), 2018, : 88 - 100
  • [6] CLUSTER ADAPTIVE TRAINING FOR DEEP NEURAL NETWORK
    Tan, Tian
    Qian, Yanmin
    Yin, Maofan
    Zhuang, Yimeng
    Yu, Kai
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 4325 - 4329
  • [7] Deep Neural Network Training with iPSO Algorithm
    Kosten, Mehmet Muzaffer
    Barut, Murat
    Acir, Nurettin
    [J]. 2018 26TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2018,
  • [8] Visualization of Feature Evolution During Convolutional Neural Network Training
    Punjabi, Arjun
    Katsaggelos, Aggelos K.
    [J]. 2017 25TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2017, : 311 - 315
  • [9] Evaluating the Visualization of What a Deep Neural Network Has Learned
    Samek, Wojciech
    Binder, Alexander
    Montavon, Gregoire
    Lapuschkin, Sebastian
    Mueller, Klaus-Robert
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 28 (11) : 2660 - 2673
  • [10] Towards Deep Neural Network Training on Encrypted Data
    Nandakumar, Karthik
    Ratha, Nalini
    Pankanti, Sharath
    Halevi, Shai
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 40 - 48
12345