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
  • [41] Understanding the learning mechanism of convolutional neural networks in spectral analysis
    Zhang, Xiaolei
    Xu, Jinfan
    Yang, Jie
    Chen, Li
    Zhou, Haibo
    Liu, Xiangjiang
    Li, Haifeng
    Lin, Tao
    Ying, Yibin
    ANALYTICA CHIMICA ACTA, 2020, 1119 : 41 - 51
  • [42] INTERPOLATION OF IRREGULARLY SAMPLED FREQUENCY RESPONSE FUNCTIONS USING CONVOLUTIONAL NEURAL NETWORKS
    Acerbi, M.
    Malvermi, R.
    Pezzoli, M.
    Antonacci, F.
    Sarti, A.
    Corradi, R.
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 950 - 954
  • [43] Prediction of Response to Stereotactic Radiosurgery for Brain Metastases Using Convolutional Neural Networks
    Cha, Yu Jin
    Jang, Won Il
    Kim, Mi-Sook
    Yoo, Hyung Jun
    Paik, Eun Kyung
    Jeong, Hee Kyung
    Youn, Sang-Min
    ANTICANCER RESEARCH, 2018, 38 (09) : 5437 - 5445
  • [44] Brain tumor segmentation in multi-spectral MRI using convolutional neural networks (CNN)
    Iqbal, Sajid
    Ghani, M. Usman
    Saba, Tanzila
    Rehman, Amjad
    MICROSCOPY RESEARCH AND TECHNIQUE, 2018, 81 (04) : 419 - 427
  • [45] Texture Synthesis Using Convolutional Neural Networks With Long-Range Consistency and Spectral Constraints
    Schreiber, Shaun
    Geldenhuys, Jaco
    de Villiers, Hendrik
    2016 PATTERN RECOGNITION ASSOCIATION OF SOUTH AFRICA AND ROBOTICS AND MECHATRONICS INTERNATIONAL CONFERENCE (PRASA-ROBMECH), 2016,
  • [46] Unraveling Spatial-Spectral Dynamics of Speech Categorization Speed Using Convolutional Neural Networks
    Moinuddin, Kazi Ashraf
    Havugimana, Felix
    Al-Fahad, Rakib
    Bidelman, Gavin M. M.
    Yeasin, Mohammed
    BRAIN SCIENCES, 2023, 13 (01)
  • [47] Acoustic emission for in situ quality monitoring in additive manufacturing using spectral convolutional neural networks
    Shevchik, S. A.
    Kenel, C.
    Leinenbach, C.
    Wasmer, K.
    ADDITIVE MANUFACTURING, 2018, 21 : 598 - 604
  • [48] Spatio-Spectral Feature Representation for Motor Imagery Classification Using Convolutional Neural Networks
    Bang, Ji-Seon
    Lee, Min-Ho
    Fazli, Siamac
    Guan, Cuntai
    Lee, Seong-Whan
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (07) : 3038 - 3049
  • [49] APPLICATION OF ARTIFICIAL INTELLIGENCE USING CONVOLUTIONAL NEURAL NETWORKS IN DIAGNOSING THE INVASION DEPTH OF ESOPHAGEAL SQUAMOUS CELL CARCINOMA
    Tokai, Yoshitaka
    Yoshio, Toshiyuki
    Fujisaki, Junko
    Aoyama, Kazuharu
    Tada, Tomohiro
    GASTROINTESTINAL ENDOSCOPY, 2019, 89 (06) : AB169 - AB169
  • [50] Diagnosing Leukemia in Blood Smear Images Using an Ensemble of Classifiers and Pre-trained Convolutional Neural Networks
    Vogado, Luis H. S.
    Veras, Rodrigo de M. S.
    Andrade, Alan R.
    de Araujo, Flavio H. D.
    e Silva, Romuere R. V.
    Aires, Kelson R. T.
    2017 30TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 2017, : 367 - 373