A new initialization method based on normed statistical spaces in deep networks

DOI10.3934/ipi.2020045OpenAlexW3048124370MaRDI QIDQ2028932

Hui Hu, Xiaofeng Ding, Tieyong Zeng, Hongfei Yang, Raymond Honfu Chan, Ya-Xin Peng

Publication date: 3 June 2021

Published in: Inverse Problems and Imaging (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/ipi.2020045

zbMATH Keywords

neural networksdeep learningmodel trainingparameters initializationparameters sharing

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) General topics in artificial intelligence (68T01)

Related Items (1)

Fully-connected tensor network decomposition for robust tensor completion problem

Uses Software

• CIFAR
• U-Net
• MobileNets
• Inception-v4
• MobileNetV2

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new initialization method for neural networks with weight sharing
• A mathematical theory of semantic development in deep neural networks

This page was built for publication: A new initialization method based on normed statistical spaces in deep networks