Motivated by the vast success of deep convolutional networks, there is a great interest in
generalizing convolutions to non-Euclidean manifolds. A major complication in comparison …

Learning workable representations of dynamical systems is becoming an increasingly
important problem in a number of application areas. By leveraging recent work connecting …

Reparameterizable densities are an important way to learn probability distributions in a
deep learning setting. For many distributions it is possible to create low-variance gradient …

A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable
of capturing topological properties of certain datasets. To remove topological obstructions …

Incorporating geometric inductive biases into models can aid interpretability and
generalization, but encoding to a specific geometric structure can be challenging due to the …

We investigate the ability of Diffusion Variational Autoencoder ($\Delta $ VAE) with unit
sphere $\mathcal {S}^ 2$ as latent space to capture topological and geometrical structure …

Deep latent variable models is a class of models that parameterise components of
probabilistic latent variable models with neural networks. This class of models can capture …

Geometric inductive biases such as spatial curvature, factorizability, or equivariance have
been shown to enable learning of latent spaces which better reflect the structure of data and …

Motivated by the vast success of deep convolutional networks, there is a great interest in
generalizing convolutions to non-Euclidean manifolds. A major complication in comparison …

This work introduces new learning methods based on neurorobotics. We develop a tool set
that enables massively parallel neurorobotics experiments in the cloud and supports …