Convolutional neural network training strategy using knowledge transfer

DOI10.13195/J.KZYJC.2017.1183MaRDI QIDQ5195392zbMATH OpenFDO

Authors Ke Luo, Anzhong Zhou, Xiao Luo

Publication date 2 October 2019

Full work available at URL https://doi.org/10.13195/J.KZYJC.2017.1183

zbMATH Keywords

convolutional neural networkfine-tuninggradient vanishingknowledge transferoverfittingpre-training

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Knowledge transfer in SVM and neural networks
• A full stage data augmentation method in deep convolutional neural network for natural image classification
• Accelerating deep neural network training with inconsistent stochastic gradient descent
• Low-rank transfer learning
• Why do deep convolutional networks generalize so poorly to small image transformations?

Cited in

(1)

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

This page was built for publication: Convolutional neural network training strategy using knowledge transfer

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5195392)