The Kernel Dynamics of Convolutional Neural Networks in Manifolds

被引：0

作者：

WU Wei ^{[1
,2
]}

JING Xiaoyuan ^{[1
]}

DU Wencai ^{[3
]}

机构：

[1] School of Computer Science,Wuhan University

[2] Institute of Deep-sea Science and Engineering,Chinese Academy of Sciences

[3] Institute of Data Science,City University of Macau

来源：

Chinese Journal of Electronics | 2020年 / 29卷 / 06期

基金：

中国国家自然科学基金;

关键词：

D O I：

暂无

中图分类号：

TP183 [人工神经网络与计算];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose a novel expression from manifolds to define Convolutional neural network(CNN).The layered structure is proceeded by integration in limited space continuously,with weights adjusted including value and direction in neural manifolds.Status transfer functions are proposed to simulate the kernel dynamics as a control matrix.We theoretically analyze the stability and controllability of kernel-based CNNs,and verify our findings by numerical experiments.

引用

页码：1185 / 1192

页数：8

共 50 条

[1] Learning dynamics of kernel-based deep neural networks in manifolds
Wu, Wei
Jing, Xiaoyuan
Du, Wencai
Chen, Guoliang
[J]. SCIENCE CHINA-INFORMATION SCIENCES, 2021, 64 (11)
[2] Learning dynamics of kernel-based deep neural networks in manifolds
Wei WU
Xiaoyuan JING
Wencai DU
Guoliang CHEN
[J]. Science China(Information Sciences), 2021, 64 (11) : 105 - 119
[3] Learning dynamics of kernel-based deep neural networks in manifolds
Wei Wu
Xiaoyuan Jing
Wencai Du
Guoliang Chen
[J]. Science China Information Sciences, 2021, 64
[4] The Kernel Dynamics of Convolutional Neural Networks in ManifoldsInspec keywordsOther keywordsKey words
Wu, Wei
Jing, Xiaoyuan
Du, Wencai
[J]. CHINESE JOURNAL OF ELECTRONICS, 2020, 29 (06) : 1185 - 1192
[5] Kernel Graph Convolutional Neural Networks
Nikolentzos, Giannis
Meladianos, Polykarpos
Tixier, Antoine Jean-Pierre
Skianis, Konstantinos
Vazirgiannis, Michalis
[J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT I, 2018, 11139 : 22 - 32
[6] Kernel Pooling for Convolutional Neural Networks
Cui, Yin
Zhou, Feng
Wang, Jiang
Liu, Xiao
Lin, Yuanqing
Belongie, Serge
[J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 3049 - 3058
[7] Geodesic Convolutional Neural Networks on Riemannian Manifolds
Masci, Jonathan
Boscaini, Davide
Bronstein, Michael M.
Vandergheynst, Pierre
[J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW), 2015, : 832 - 840
[8] Vector-kernel convolutional neural networks
Ou, Jun
Li, Yujian
[J]. NEUROCOMPUTING, 2019, 330 : 253 - 258
[9] On the regularization of convolutional kernel tensors in neural networks
Guo, Pei-Chang
Ye, Qiang
[J]. LINEAR & MULTILINEAR ALGEBRA, 2022, 70 (12): : 2318 - 2330
[10] Convolutional Neural Networks on Manifolds: From Graphs and Back
Wang, Zhiyang
Ruiz, Luana
Ribeiro, Alejandro
[J]. 2022 56TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2022, : 356 - 360

← 1 2 3 4 5 →