the.ai

Data / Schedules

verified

Curriculum

Show easy examples first and hard ones later, as a teacher would. The idea is old and intuitive and its record in deep learning is mixed — it helps clearly in some settings and does nothing in others, and which is which is not well predicted in advance.

Viz primitive · budget-spliteasy-examples = 6

easy-examples holds 50% of the budget; rest holds the remaining 50%.

Easy examples early in training against hard ones held back, in examples. Drag the curriculum up to watch the early distribution simplify — the claim is about how fast a good solution is reached, not about which one.

6

Reviewed by opendroid · 2026-08-18

Origin · not linkable

  • Bengio et al. 2009 — Curriculum Learning · ICML 2009 · doi:10.1145/1553374.1553380