Preprint
Modeling Teacher-Student Techniques in Deep Neural Networks for Knowledge Distillation
Abstract
Knowledge distillation (KD) is a new method for transferring knowledge of a
structure under training to another one. The typical application of KD is in
Authors
Abbasi S; Hajabdollahi M; Karimi N; Samavi S
Publication date
December 31, 2019
DOI
10.48550/arxiv.1912.13179
Preprint server
arXiv