Balanced joint maximum mean discrepancy for deep transfer learning

DOI10.1142/S0219530520400035MaRDI QIDQ4995048zbMATH OpenOpenAlexFDO

Authors Chuangji Meng, Cunlu Xu, Qin Lei, Wei Su, Jinzhao Wu

Publication date 23 June 2021

Published in Analysis and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/s0219530520400035

zbMATH Keywords

balanced distribution adaptationdeep learningdomain adaptationjoint distribution adaptationtransfer learning

Mathematics Subject Classification ID

Multilinear algebra, tensor calculus (15A69) Linear operators in reproducing-kernel Hilbert spaces (including de Branges, de Branges-Rovnyak, and other structured spaces) (47B32) Artificial neural networks and deep learning (68T07) Applications of mathematical programming (90C90)

Recommendations

• Deep Transfer Metric Learning
• A theoretical framework for deep transfer learning
• Balanced distribution adaptation and instance based transfer learning algorithm
• Matching component analysis for transfer learning

Cites work

• A kernel two-sample test
• Deep distributed convolutional neural networks: universality
• Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
• Deep neural networks for rotation-invariance approximation and learning
• Natural language processing (almost) from scratch
• Universality of deep convolutional neural networks
• Unsupervised Domain Adaptation With Label and Structural Consistency

Cited in

(1)

• Mitigating barren plateaus with transfer-learning-inspired parameter initializations

Describes a project that uses

Uses Software

• ImageNet
• AlexNet
• Caffe

This page was built for publication: Balanced joint maximum mean discrepancy for deep transfer learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4995048)