MetaFun: meta-learning with iterative functional updates
We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resem...
Главные авторы: | Xu, J, Ton, J-F, Kim, H, Kosiorek, AR, Teh, YW |
---|---|
Формат: | Journal article |
Язык: | English |
Опубликовано: |
MLResearch Press
2020
|
Схожие документы
-
MetaFun: unveiling sex-based differences in multiple transcriptomic studies through comprehensive functional meta-analysis
по: Pablo Malmierca-Merlo, и др.
Опубликовано: (2024-08-01) -
Correction: MetaFun: unveiling sex-based differences in multiple transcriptomic studies through comprehensive functional meta-analysis
по: Pablo Malmierca-Merlo, и др.
Опубликовано: (2024-09-01) -
Noise contrastive meta-learning for conditional density estimation using kernel mean embeddings
по: Ton, J-F, и др.
Опубликовано: (2021) -
Set transformer: A framework for attention-based permutation-invariant neural networks
по: Lee, J, и др.
Опубликовано: (2019) -
Model updating for fun kart chassis
по: Mohd Sahril, Mohd Fouzi
Опубликовано: (2008)