Decomposition and composition of deep convolutional neural networks and training acceleration via sub-network transfer learning

DOI10.1553/ETNA_VOL56S157OpenAlexW4214664751WikidataQ111518721 ScholiaQ111518721MaRDI QIDQ2672198

Linyan Gu, Jia Liu, Wei Zhang, Xiao-Chuan Cai

Publication date: 8 June 2022

Published in: ETNA. Electronic Transactions on Numerical Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1553/etna_vol56s157

zbMATH Keywords

domain decompositiontransfer learningparallel trainingdeep convolutional neural networksdecomposition and composition

Mathematics Subject Classification ID

Analysis of algorithms (68W40) Parallel algorithms in computer science (68W10)

Related Items (1)

Learning adaptive coarse basis functions of FETI-DP

Uses Software

• CIFAR
• ImageNet
• SSD
• U-Net
• AlexNet
• Faster R-CNN

Cites Work

• A nonlinear elimination preconditioned inexact Newton method for blood flow problems in human artery with stenosis
• Unnamed Item
• Unnamed Item

This page was built for publication: Decomposition and composition of deep convolutional neural networks and training acceleration via sub-network transfer learning