Born Again Neural Networks
Pages: 1607 - 1616
Published: Jul 3, 2018
Abstract
Knowledge Distillation (KD) consists of transferring “knowledge” from one machine learning model (the teacher) to another (the student). Commonly, the teacher is a high-capacity model with formidable performance, while the student is more compact. By transferring knowledge, one hopes to benefit from the student’s compactness, without sacrificing too much performance. We study KD from a new perspective: rather than compressing models, we train...
Paper Details
Title
Born Again Neural Networks
Published Date
Jul 3, 2018
Pages
1607 - 1616
Citation AnalysisPro
You’ll need to upgrade your plan to Pro
Looking to understand the true influence of a researcher’s work across journals & affiliations?
- Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
- Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.
Notes
History