AI & MLCoreAIML-LM-003
Autoregressive Factorization
Joint probability as a product of nexts: the chain rule behind generation.
- Difficulty
- 2 / 5
- Importance
- 5 / 5
- Study time
- 1–2 h
- Kind of work
- Mixed
Why it matters
The learner can factor a tiny sequence probability into next-token conditionals.