Term tag: meta-learning

Few-shot Learning (FSL)

Teaching a model a task by showing it a handful of worked examples. In its modern form, few-shot prompting, no weights are updated at all.

Meta-Learning

Learning to learn: training a model across thousands of tiny tasks so it adapts from a handful of examples — and how that differs from fine-tuning.

One-shot Learning

Learning a new class from exactly one example — and the split that matters: one-shot prompting updates no weights; classical one-shot training does.

Self-Improving AI (SIAI)

Self-improving AI (SIAI) is a system that upgrades its own capabilities. Real today only in narrow forms like self-play; the recursive version is speculative.