Google publishes Distilling the Knowledge in a Neural Network on arXiv

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Distilling the Knowledge in a Neural Network released on arXiv

Why it matters

Formalized distillation, which transfers a large model's knowledge to a small model. The root of today's small-model lineage

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/1503.02531

Added in Week 35, 2026 · See that week

On the map — ⓪ Prehistory line

  1. Previous stopNeural Machine Translation by Jointly Learning to Align and Translate
  2. This record · stopGoogle publishes Distilling the Knowledge in a Neural Network on arXiv
  3. Next stopAlphaGo–Lee Sedol five-game match in Seoul ends (Mar 9–15)
See it on the map

Nearby on the same axis

Human-level control through deep reinforcement learningPaperGoogle publishes Batch Normalization on arXivPaperRonneberger, Fischer and Brox publish U-Net on arXivPaperAdam: A Method for Stochastic OptimizationPaper