한국어EN
Prehistory — From Neural Networks to the TransformerJonas Gehring et al. (Facebook AI Research)FAIR

Convolutional Sequence to Sequence Learning (ConvS2S) released on arXiv

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

Convolutional Sequence to Sequence Learning (ConvS2S) released on arXiv

Why it matters

Performed translation with convolutions alone, showing the race to move beyond recurrence just before the Transformer

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

Paperarxiv.orghttps://arxiv.org/abs/1705.03122

Added in Week 35, 2026 · See that week

On the map — ⓪ Prehistory line

  1. Previous stopAlphaGo–Lee Sedol five-game match in Seoul ends (Mar 9–15)
  2. This record · stopConvS2S
  3. Next stopNo later stop yet
See it on the map

Nearby on the same axis

In-Datacenter Performance Analysis of a Tensor Processing UnitPaperZhu et al. publish CycleGAN on arXivPaperFinn, Abbeel and Levine publish Model-Agnostic Meta-Learning (MAML) on arXivPaperArjovsky, Chintala and Bottou publish Wasserstein GAN on arXivPaper