// ⬡ Deep Learning Foundations
Sequence-to-Sequence Learning
An encoder reads a sequence and a decoder generates another.
序列到序列（Seq2Seq） 2014 Foundational core
IN PLAIN WORDS
An encoder compresses the input and a decoder emits the output word by word, trained end to end. Its bottleneck motivated attention.
Used in: Early neural machine translation
TIMELINE · prerequisites → this → what builds on it
01Original paper
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le · 2014
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
Related:Transformer & Self-Attention
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
On learning paths:Zero to Deep Learning
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
seq2seq)