Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.¶
Finn, C., Abbeel, P., & Levine, S. (2017). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Proceedings of the 34th International Conference on Machine Learning (ICML), 1126-1135.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Metaplasticity
- In machine learning, meta-learning, learning-rate schedulers, and adaptive optimizers maintain per-parameter or per-task adaptation rates that themselves update on history, and continual-learning regularizers raise stiffness on weights important to prior tasks.
This sourceFormalizes learning-to-learn—optimizing the adaptation procedure itself from accumulated task history.
Supported in partVerified against the work's full text
MAML supplies a model-agnostic meta-learning algorithm whose initialization is trained across many tasks, but it states nothing about maintained per-parameter or per-task adaptation rates.
“We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning.”
- In machine learning, meta-learning, learning-rate schedulers, and adaptive optimizers maintain per-parameter or per-task adaptation rates that themselves update on history, and continual-learning regularizers raise stiffness on weights important to prior tasks.
Verification¶
Does it exist? Not checked yet. This entry carries no identifier to resolve. It was extracted from the citation as written in the article, normalized, and deduplicated against the rest of the registry.
Does it back the claim? Read against the text for 1 of 1 citation: 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:89009d967320 · see in the full table