arrow
返回

Frames Learned by Prime Convolution Layers in a Deep Learning Framework

delete2021-07-01
delete1
PRE
AI
A
Abdourrahmane M. Atto *
R
Rosie R. Bisset
E
Emmanuël Trouvé
DOI:10.1109/TNNLS.2020.3009059delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
This brief addresses understandability of modern machine learning networks with respect to the statistical properties of their convolution layers. It proposes a set of tools for categorizing a convolution layer in terms of kernel property (meanlet, differencelet, or distrotlet) or kernel sequence property (frame spectra and intralayer correlation matrix). These tools are expected to be relevant for determining the generalization capabilities of a convolutional neural network. In particular, this brief highlights that the less frequency penalizing network among AlexNet, GoogleNet, RESNET101, and VGG19 is the more relevant one in terms of solutions for low-level ice-sheet feature enhancement.
Keyword:
Kernel
Convolution
Standards
Training
Harmonic analysis
Machine learning
Learning systems
Convolution frames
convolutional neural network (CNN)
deep learning
differencelet
distrotlet
meanlet
wavelet
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Neural Networks and Learning Systems 封面图
IEEE Transactions on Neural Networks and Learning Systems
IF:
8.9
论文数:
7.5K
被引数:
7.2W

机构

U
Universite Savoie Mont Blanc
学者数:
5.4K
论文数: 4.0K
被引数: 18
U
University of Edinburgh
学者数:
5.2W
论文数: 4.6W
被引数: 71
引用论文

引用论文

Establishment and characterization of a human non‐secretory plasmacytoid cell line and its hybridization with human B cells
err2006-07-17
err0
PREAI
errR. E. Ritts; Alejandro Ruiz‐Argüelles; Karin G. Weyl; Anne L. Bradley; Bernadette Weihmeir; Deborah J. Jacobsen; Bonnie L. Strehlo
err分享
err收藏
ImageNet Large Scale Visual Recognition ChallengeImageNet大规模视觉识别挑战
err2015-04-11
err2.7W
PREAI
errRussakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li
err分享
err收藏
err分享
err收藏
学者 查看更多内容