On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity

被引:0
|
作者
Szolnoky, Vincent [1 ]
Andersson, Viktor [2 ]
Kulcsar, Balazs [2 ]
Jornsten, Rebecka [1 ]
机构
[1] Chalmers Univ Technol, Dept Math Sci, Chalmers Tvargata 3, S-41296 Gothenburg, Sweden
[2] Chalmers Univ Technol, Dept Elect Engn, Chalmersplatsen 4, S-41296 Gothenburg, Sweden
基金
瑞典研究理事会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Most complex machine learning and modelling techniques are prone to over-fitting and may subsequently generalise poorly to future data. Artificial neural networks are no different in this regard and, despite having a level of implicit regularisation when trained with gradient descent, often require the aid of explicit regularisers. We introduce a new framework, Model Gradient Similarity (MGS), that (1) serves as a metric of regularisation, which can be used to monitor neural network training, (2) adds insight into how explicit regularisers, while derived from widely different principles, operate via the same mechanism underneath by increasing MGS, and (3) provides the basis for a new regularisation scheme which exhibits excellent performance, especially in challenging settings such as high levels of label noise or limited sample sizes.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] Seeking Interpretability and Explainability in Binary Activated Neural Networks
    Leblanc, Benjamin
    Germain, Pascal
    EXPLAINABLE ARTIFICIAL INTELLIGENCE, PT I, XAI 2024, 2024, 2153 : 3 - 20
  • [32] Semantic Interpretability of Convolutional Neural Networks by Taxonomy Extraction
    Horta, Vitor A. C.
    Sobczyk, Robin
    Stol, Maarten C.
    Mileo, Alessandra
    NEURAL-SYMBOLIC LEARNING AND REASONING 2023, NESY 2023, 2023,
  • [33] Structural Compression of Convolutional Neural Networks with Applications in Interpretability
    Abbasi-Asl, Reza
    Yu, Bin
    FRONTIERS IN BIG DATA, 2021, 4
  • [34] IMPROVING THE INTERPRETABILITY OF DEEP NEURAL NETWORKS WITH STIMULATED LEARNING
    Tan, Shawn
    Sim, Khe Chai
    Gales, Mark
    2015 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2015, : 617 - 623
  • [35] Optimizing for interpretability in deep neural networks with tree regularization
    Wu M.
    Parbhoo S.
    Hughes M.C.
    Roth V.
    Doshi-Velez F.
    Journal of Artificial Intelligence Research, 2021, 72
  • [36] Interpretability of Recurrent Neural Networks Trained on Regular Languages
    Oliva, Christian
    Lago-Fernandez, Luis F.
    ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2019, PT II, 2019, 11507 : 14 - 25
  • [37] Improving Interpretability of Deep Neural Networks with Semantic Information
    Dong, Yinpeng
    Su, Hang
    Zhu, Jun
    Zhang, Bo
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 975 - 983
  • [38] Regional Tree Regularization for Interpretability in Deep Neural Networks
    Wu, Mike
    Parbhoo, Sonali
    Hughes, Michael C.
    Kindle, Ryan
    Celi, Leo
    Zazzi, Maurizio
    Roth, Volker
    Doshi-Velez, Finale
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 6413 - 6421
  • [39] Interpretability with Relevance Aggregation in Neural Networks for Absenteeism Prediction
    Gomes Junior, Julio Marcos
    Lopes, Fabricio Martins
    2022 IEEE-EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL AND HEALTH INFORMATICS (BHI) JOINTLY ORGANISED WITH THE IEEE-EMBS INTERNATIONAL CONFERENCE ON WEARABLE AND IMPLANTABLE BODY SENSOR NETWORKS (BSN'22), 2022,
  • [40] A Scoring Method for Interpretability of Concepts in Convolutional Neural Networks
    Gurkan, Mustafa Kagan
    Arica, Nafiz
    Vural, Fato Yarman
    2022 30TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU, 2022,