AI & MLCoreAIML-SEQ-007
Sequence-to-Sequence Models
An encoder compresses an input sequence, a decoder generates an output sequence: the bottleneck attention was invented to fix.
- Difficulty
- 2 / 5
- Importance
- 5 / 5
- Study time
- 1–2 h
- Kind of work
- Mixed
Why it matters
The learner can trace an encoder-decoder over a short input and explain why a single fixed context vector degrades on long inputs.