direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Maschnielles Lernen


Representation Change in Model-Agnostic Meta-Learning
Zitatschlüssel Goerttler2022
Autor Goerttler, T. and Müller, L. and Obermayer, K.
Jahr 2022
Journal ICLR Blog Track
Zusammenfassung Last year, an exciting adaptation of one of the most popular optimization-based meta-learning approaches, model-agnostic meta-learning (MAML) [Finn et al., 2017], was proposed in ▶ Jaehoon Oh, Hyungjun Yoo, ChangHwan Kim, Se-Young Yun (ICLR, 2021) BOIL: Towards Representation Change for Few-shot Learning The authors adapt MAML by freezing the last layer to force body only inner learning (BOIL). Interestingly, this is complementary to ANIL (almost no inner loop) proposed in ▶ Aniruddh Raghu, Maithra Raghu, Samy Bengio, Oriol Vinyals (ICLR, 2020) Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML Both papers attempt to understand the success of MAML and improve it. Oh et al. [2021] compare BOIL, ANIL, and MAML and show that both improve the performance of MAML. Albeit, BOIL outperforms ANIL, especially when the task distribution varies between training and testing.
Typ der Publikation Selected:structured selected:main selected:quantify
Link zur Originalpublikation Download Bibtex Eintrag

Zusatzinformationen / Extras


Schnellnavigation zur Seite über Nummerneingabe