What is Model-agnostic meta-learning (MAML)?

Model-agnostic meta-learning (MAML)

Model-agnostic meta-learning (MAML): A meta-learning method that finds an initial set of weights from which a few gradient steps solve any of many related tasks.

Related terms

LIME (Local Interpretable Model-agnostic Explanations)
Meta-learning
Model-based reinforcement learning
Automated machine learning (AutoML)
Autoregressive model
Cascade (model cascade)
Consistency model
Continual learning

Browse the full glossary →