Učitavanje...

Information-Theoretic Generalization Bounds for Meta-Learning and Applications

Meta-learning, or “learning to learn”, refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key performance measure for meta-learning is the meta-generalization ga...

Cijeli opis

Spremljeno u:
Bibliografski detalji
Izdano u:Entropy (Basel)
Glavni autori: Jose, Sharu Theresa, Simeone, Osvaldo
Format: Artigo
Jezik:Inglês
Izdano: MDPI 2021
Teme:
Online pristup:https://ncbi.nlm.nih.gov/pmc/articles/PMC7835863/
https://ncbi.nlm.nih.gov/pubmed/33478002
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3390/e23010126
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!