Diagnosing Convolutional Neural Networks using their Spectral Response

被引:0
|
作者
Stamatescu, Victor [1 ]
McDonnell, Mark D. [2 ]
机构
[1] Def Sci & Technol Grp, Edinburgh, SA 5111, Australia
[2] Univ South Australia, Sch Informat Technol & Math Sci, Computat Learning Syst Lab Cls Lab Org, Mawson Lakes, SA 5095, Australia
关键词
D O I
暂无
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
Convolutional Neural Networks (CNNs) are a class of artificial neural networks whose computational blocks use convolution, together with other linear and non-linear operations, to perform classification or regression. This paper explores the spectral response of CNNs and its potential use in diagnosing problems with their training. We measure the gain of CNNs trained for image classification on ImageNet and observe that the best models are also the most sensitive to perturbations of their input. Further, we perform experiments on MNIST and CIFAR-10 to find that the gain rises as the network learns and then saturates as the network converges. Moreover, we find that strong gain fluctuations can point to overfitting and learning problems caused by a poor choice of learning rate. We argue that the gain of CNNs can act as a diagnostic tool and potential replacement for the validation loss when hold-out validation data are not available.
引用
收藏
页码:603 / 610
页数:8
相关论文
共 50 条
  • [21] Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks
    Rafif, Sulthan
    Pratama, Mochamad Arfan Ravy Wahyu
    Azhar, Mohammad Faris
    Ibad, Ahmad Mustafidul
    Muflikhah, Lailil
    Yudistira, Novanto
    arXiv,
  • [22] Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks
    Rafif, Sulthan
    Azhar, Mohammad Faris
    Wahyu Pratama, Mochamad Arfan Ravy
    Ibad, Ahmad Mustafidul
    Yudistira, Novanto
    Muflikhah, Lailil
    ACM International Conference Proceeding Series, 2023, : 210 - 216
  • [23] Application of convolutional neural networks for stellar spectral classification
    Sharma, Kaushal
    Kembhavi, Ajit
    Kembhavi, Aniruddha
    Sivarani, T.
    Abraham, Sheelu
    Vaghmare, Kaustubh
    MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2020, 491 (02) : 2280 - 2300
  • [24] Prediction of radiosurgery response of brain metastases using convolutional neural networks
    Cha, Y.
    Kim, M. S.
    Cho, C. K.
    Yoo, H.
    Jang, W. I.
    Seo, Y. S.
    Kang, J. K.
    Paik, E. K.
    RADIOTHERAPY AND ONCOLOGY, 2017, 123 : S328 - S328
  • [25] Modeling yield response to crop management using convolutional neural networks
    Barbosa, Alexandre
    Trevisan, Rodrigo
    Hovakimyan, Naira
    Martin, Nicolas F.
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 170
  • [26] Convolutional Neural Networks for Survey Response Classification
    Stein, Nikolai
    Oberdorf, Felix
    Pirner, Jonas
    AMCIS 2020 PROCEEDINGS, 2020,
  • [27] Convolutional Neural Networks and Stokes Response Functions
    Centeno, Rebecca
    Flyer, Natasha
    Mukherjee, Lipi
    Egeland, Ricky
    Casini, Roberto
    Aleman, Tanausu del Pino
    Rempel, Matthias
    ASTROPHYSICAL JOURNAL, 2022, 925 (02):
  • [28] Spectral-Spatial Hyperspectral Image Classification Using Cascaded Convolutional Neural Networks
    Dovletov, Gurbandurdy
    Hegemann, Tobias
    Pauli, Josef
    IMAGE ANALYSIS, 2019, 11482 : 78 - 89
  • [29] Multicomponent Raman spectral regression using complete and incomplete models and convolutional neural networks
    Boateng, Derrick
    Hu, Chuanzhen
    Dai, Yichuan
    Chu, Kaiqin
    Du, Jun
    Smith, Zachary J.
    ANALYST, 2022, 147 (20) : 4607 - 4615
  • [30] Spectral-spatial classification of hyperspectral images using deep convolutional neural networks
    Yue, Jun
    Zhao, Wenzhi
    Mao, Shanjun
    Liu, Hui
    REMOTE SENSING LETTERS, 2015, 6 (06) : 468 - 477