One of the main challenges in modern deep learning is to understand why ...
Bayesian neural networks often approximate the weight-posterior with a
G...
In recent decades, advancements in motion learning have enabled robots t...
A recent line of work has established intriguing connections between the...
Latent space geometry has shown itself to provide a rich and rigorous
fr...
For robots to work alongside humans and perform in unstructured environm...
Stochastic generative models enable us to capture the geometric structur...
Riemannian manifolds provide a principled way to model nonlinear geometr...
A common assumption in generative models is that the generator immerses ...
Variational Autoencoders (VAEs) represent the given data in a low-dimens...
We propose a fast, simple and robust algorithm for computing shortest pa...
Deep generative models are tremendously successful in learning
low-dimen...
Deep generative models provide a systematic way to learn nonlinear data
...
The multivariate normal density is a monotonic function of the distance ...