Revisiting Orthogonality Regularization: A Study for Convolutional Neural Networks in Image Classification

Recent research in deep Convolutional Neural Networks(CNN) faces the challenges of vanishing/exploding gradient issues, training instability, and feature redundancy. Orthogonality Regularization(OR), which introduces a penalty function considering the orthogonality of neural networks, could be a rem...

Descrición completa

Detalles Bibliográficos

Principais autores:	Taehyeon Kim, Se-Young Yun
Formato:	Artigo
Idioma:	Inglês
Publicado:	IEEE 2022-01-01
Series:	IEEE Access
Assuntos:	Deep neural network (DNN) kernel orthogonality regularization convolutional neural network (CNN) regularization image classification
Acceso en liña:	https://ieeexplore.ieee.org/document/9804718/
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!