A theoretical framework for deep transfer learning

DOI10.1093/IMAIAI/IAW008MaRDI QIDQ4603722zbMATH OpenOpenAlexFDO

Authors Tomer Galanti, Lior Wolf, Tamir Hazan

Publication date 19 February 2018

Published in Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/75f24d175c0f30138063afc841e825ff211090c3

zbMATH Keywords

deep learningtransfer learningPAC learningPAC-Bayesian

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• A deep learning framework for hybrid heterogeneous transfer learning
• On universal transfer learning
• On Universal Transfer Learning
• scientific article; zbMATH DE number 7156178
• A theory of transfer learning with applications to active learning

Cites work

• scientific article; zbMATH DE number 5957307 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 823069 (Why is no real title available?)
• scientific article; zbMATH DE number 1448976 (Why is no real title available?)
• 10.1162/153244302760200704
• A theory of learning from different domains
• A theory of the learnable
• Learnability and the Vapnik-Chervonenkis dimension
• Learnability, stability and uniform convergence
• Learning from multiple sources
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• On the density of families of sets
• Sample Selection Bias Correction Theory
• Understanding machine learning. From theory to algorithms

Cited in

(12)

• Mitigating barren plateaus with transfer-learning-inspired parameter initializations
• scientific article; zbMATH DE number 1302403 (Why is no real title available?)
• On universal transfer learning
• scientific article; zbMATH DE number 7156178 (Why is no real title available?)
• Adaptive transfer learning
• Transfer bounds for linear feature learning
• A theory of transfer learning with applications to active learning
• Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks
• Advances in domain adaptation theory
• Risk bound of transfer learning using parametric feature mapping and its application to sparse coding
• Balanced joint maximum mean discrepancy for deep transfer learning
• Transfer Learning under High-dimensional Generalized Linear Models

Describes a project that uses

Uses Software

• ImageNet
• DeepFace
• AlexNet

This page was built for publication: A theoretical framework for deep transfer learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4603722)