作者: Shimon Whiteson , Katja Hofmann , Vitaly Kurin , Luisa Zintgraf , Kyriacos Shiarli
DOI:
关键词:
摘要: We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable. CAVIA partitions the model …