Meta-learning using privileged information for dynamics

B Day, A Norcliffe, J Moss, P Liò - arXiv preprint arXiv:2104.14290, 2021 - arxiv.org
Neural ODE Processes approach the problem of meta-learning for dynamics using a latent
variable model, which permits a flexible aggregation of contextual information. This flexibility …
被引用次数：4 相关文章 HTML 版

Meta-learning using privileged information for dynamics

B Day, A Norcliffe, J Moss, P Liò - arXiv e-prints, 2021 - ui.adsabs.harvard.edu
Neural ODE Processes approach the problem of meta-learning for dynamics using a latent
variable model, which permits a flexible aggregation of contextual information. This flexibility …

Meta-learning using privileged information for dynamics

B Day, ALI Norcliffe, J Moss, P Liò - Learning to Learn-Workshop at ICLR … - openreview.net
Neural ODE Processes approach the problem of meta-learning for dynamics using a latent
variable model, which permits a flexible aggregation of contextual information. This flexibility …
[PDF] github.io

[PDF][PDF] META-LEARNING USING PRIVILEGED INFORMATION FOR DYNAMICS

B Day, A Norcliffe, J Moss, P Lio - simdl.github.io
Neural ODE Processes approach the problem of meta-learning for dynamics using a latent
variable model, which permits a flexible aggregation of contextual information. This flexibility …
[PDF] researchgate.net

[PDF][PDF] META-LEARNING USING PRIVILEGED INFORMATION FOR DYNAMICS

B Day, A Norcliffe, J Moss, P Lio - researchgate.net
Neural ODE Processes approach the problem of meta-learning for dynamics using a latent
variable model, which permits a flexible aggregation of contextual information. This flexibility …

Meta-learning using privileged information for dynamics

B Day, A Norcliffe, J Moss, P Liò - simdl.github.io
Background: Neural ODEs (NODE), NPs, and NDPs tl; dr: Can we better meta-learn
dynamics if we have access to high-level descriptions at training time?(Yes.) 1. Neural ODE …