-
Learning Flat Latent Manifolds with VAEs
Measuring the similarity between data points often requires domain knowl...
02/12/2020 ∙ by Nutan Chen, et al. ∙
16
∙
share
read it
-
Increasing the Generalisaton Capacity of Conditional VAEs
We address the problem of one-to-many mappings in supervised learning, w...
08/23/2019 ∙ by Alexej Klushyn, et al. ∙
21
∙
share
read it
-
Learning Hierarchical Priors in VAEs
We propose to learn a hierarchical prior in the context of variational a...
05/13/2019 ∙ by Alexej Klushyn, et al. ∙
0
∙
share
read it
-
Fast Approximate Geodesics for Deep Generative Models
The length of the geodesic between two data points along the Riemannian ...
12/19/2018 ∙ by Nutan Chen, et al. ∙
10
∙
share
read it
-
Active Learning based on Data Uncertainty and Model Sensitivity
Robots can rapidly acquire new skills from demonstrations. However, duri...
08/06/2018 ∙ by Nutan Chen, et al. ∙
8
∙
share
read it
-
Metrics for Deep Generative Models
Neural samplers such as variational autoencoders (VAEs) or generative ad...
11/03/2017 ∙ by Nutan Chen, et al. ∙
0
∙
share
read it
