New regularization methods for convolutional kernel tensors

New regularization methods for convolutional kernel tensors

Convolution is a very basic and important operation for convolutional neural networks. For neural network training, how to bound the convolutional layers is a currently popular research topic. Each convolutional layer is represented by a tensor, which corresponds to a structured transformation matri...

Full description

Bibliographic Details
Main Author: Pei-Chang Guo
Format: Article
Language:English
Published: AIMS Press 2023-09-01
Series:AIMS Mathematics
Subjects:
regularization
singular values
doubly blocked banded toeplitz matrices
convolutional kernel tensor
Online Access:https://www.aimspress.com/article/doi/10.3934/math.20231335?viewType=HTML

Internet

https://www.aimspress.com/article/doi/10.3934/math.20231335?viewType=HTML

Similar Items