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
  • [21] Compressing deep-quaternion neural networks with targeted regularisation
    Vecchi, Riccardo
    Scardapane, Simone
    Comminiello, Danilo
    Uncini, Aurelio
    CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2020, 5 (03) : 172 - 176
  • [22] Regularisation of neural networks for improved load forecasting in the power system
    Osowski, S
    Siwek, K
    IEE PROCEEDINGS-GENERATION TRANSMISSION AND DISTRIBUTION, 2002, 149 (03) : 340 - 344
  • [23] Pruning of Deep Spiking Neural Networks through Gradient Rewiring
    Chen, Yanqi
    Yu, Zhaofei
    Fang, Wei
    Huang, Tiejun
    Tian, Yonghong
    PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 1713 - 1721
  • [24] Sentence Semantic Similarity Model Using Convolutional Neural Networks
    Karthiga M.
    Sountharrajan S.
    Suganya E.
    Sankarananth S.
    EAI Endorsed Transactions on Energy Web, 2021, 8 (35) : 1 - 6
  • [25] An improved collaborative filtering similarity model based on neural networks
    Bi, Xiaodong
    Jin, Weizu
    2015 INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION, BIG DATA AND SMART CITY (ICITBS), 2016, : 85 - 89
  • [26] ENHANCING INTERPRETABILITY AND FIDELITY IN CONVOLUTIONAL NEURAL NETWORKS THROUGH DOMAIN-INFORMED KNOWLEDGE INTEGRATION
    Agbangba, Codjo Emile
    Toha, Rodeo Oswald Y.
    Bello, Abdou Wahidi
    Adetola, Jamal
    ADVANCES AND APPLICATIONS IN STATISTICS, 2024, 91 (09) : 1165 - 1194
  • [27] Interpretability Analysis of Convolutional Neural Networks for Crack Detection
    Wu, Jie
    He, Yongjin
    Xu, Chengyu
    Jia, Xiaoping
    Huang, Yule
    Chen, Qianru
    Huang, Chuyue
    Eslamlou, Armin Dadras
    Huang, Shiping
    BUILDINGS, 2023, 13 (12)
  • [28] Interpretability for Neural Networks from the Perspective of Probability Density
    Lu, Lu
    Pan, Tingting
    Zhao, Junhong
    Yang, Jie
    2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, : 1502 - 1507
  • [29] Interpretability Analysis of Deep Neural Networks With Adversarial Examples
    Dong Y.-P.
    Su H.
    Zhu J.
    Zidonghua Xuebao/Acta Automatica Sinica, 2022, 48 (01): : 75 - 86
  • [30] Challenges in Interpretability of Neural Networks for Eye Movement Data
    Kumar, Ayush
    Howlader, Prantik
    Garcia, Rafael
    Weiskopf, Daniel
    Mueller, Klaus
    ETRA 2020 SHORT PAPERS: ACM SYMPOSIUM ON EYE TRACKING RESEARCH & APPLICATIONS, 2020,