Distilling the Knowledge in a Neural Network

Soft targets from a big model teach a small one almost everything that matters.

What this paper explains

Soft targets from a big model teach a small one almost everything that matters.

What to notice

• What problem the paper set out to solve, and why earlier approaches stalled there.
• The key mechanism or formula introduced, in the authors' own terms.
• Which results held up, and which assumptions later work relaxed.

How to read it

Read the abstract and introduction for the problem setup, then the method section for the core mechanism. Skim experiments for what actually moved.

Sources

• Authors: Hinton et al. (2015)