Drop-activation: implicit parameter reduction and harmonious regularization

DOI10.1007/s42967-020-00085-3zbMath1477.68280arXiv1811.05850OpenAlexW3095528602MaRDI QIDQ2667354

Senwei Liang, Haizhao Yang, Yuehaw Khoo

Publication date: 24 November 2021

Published in: Communications on Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.05850

zbMATH Keywords

regularizationimage classificationdeep learningoverfitting

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07) Image analysis in multivariate analysis (62H35) Computing methodologies for image processing (68U10)

Related Items (1)

Drop-Activation

Uses Software

• MNIST
• CIFAR
• ImageNet
• GitHub
• EMNIST
• mixup
• Zoneout
• AlexNet
• AutoAugment

Cites Work

• Wide neural networks of any depth evolve as linear models under gradient descent ^*
• Unnamed Item

This page was built for publication: Drop-activation: implicit parameter reduction and harmonious regularization