한국어EN
Prehistory — From Neural Networks to the TransformerDiederik P. Kingma, Max Welling

Kingma and Welling publish Auto-Encoding Variational Bayes on arXiv

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

Auto-Encoding Variational Bayes released on arXiv — the VAE and the reparameterization trick

Why it matters

Made it possible to train probabilistic generative models with backpropagation, becoming one pillar of the generative model lineage

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

Paperarxiv.orghttps://arxiv.org/abs/1312.6114

Added in Week 35, 2026 · See that week

On the map — ⓪ Prehistory line

  1. Previous stopAlexNet
  2. This recordKingma and Welling publish Auto-Encoding Variational Bayes on arXiv
  3. Next stopNeural Machine Translation by Jointly Learning to Align and Translate
See it on the map

Same week

DeepMind publishes Playing Atari with Deep Reinforcement Learning on arXivPaper

Nearby on the same axis

DeepMind publishes Playing Atari with Deep Reinforcement Learning on arXivPaperGoogle confirms its acquisition of DeepMindPressCho et al. publish Learning Phrase Representations using RNN Encoder-DecoderPaperGoodfellow et al. publish Generative Adversarial Networks on arXivPaper