The Variational Homoencoder: Learning to learn high capacity generative models from few examples
© 34th Conference on Uncertainty in Artificial Intelligence 2018. All rights reserved. Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. However, when this generative model...
Main Authors: | Hewitt, Luke B. (Author), Nye, Maxwell I. (Author), Gane, Andreea (Author), Jaakkola, Tommi (Author), Tenenbaum, Joshua B. (Author) |
---|---|
Other Authors: | MIT-IBM Watson AI Lab (Contributor) |
Format: | Article |
Language: | English |
Published: |
2021-11-05T20:11:24Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Direct optimization through arg max for discrete variational auto-encoder
by: Gane, Andreea, et al.
Published: (2021) -
Meta-learning for semi-supervised few-shot classification
by: Tenenbaum, Joshua B
Published: (2020) -
Infinite mixture prototypes for few-shot learning
by: Allen, Kelsey Rebecca, et al.
Published: (2021) -
Building generative models over discrete structures : from graphical models to deep learning
by: Gane, Georgiana Andreea.
Published: (2019) -
Few-shot Conformal Prediction with Auxiliary Tasks
by: Fisch, Adam, et al.
Published: (2022)