We propose to learn a hierarchical prior in the context of variational autoencoders to avoid
the over-regularisation resulting from a standard normal prior distribution. To incentivise an …

The Science of Deep Learning emerged from courses taught by the author that have
provided thousands of students with training and experience for their academic studies, and …

A common assumption in generative models is that the generator immerses the latent space
into a Euclidean ambient space. Instead, we consider the ambient space to be a …

This article presents an overview of robot learning and adaptive control applications that can
benefit from a joint use of Riemannian geometry and probabilistic representations. The roles …

Deep generative models have demonstrated successful applications in learning non-linear
data distributions through a number of latent variables and these models use a non-linear …

Measuring the similarity between data points often requires domain knowledge, which can
in parts be compensated by relying on unsupervised methods such as latent-variable …

We study how to optimize the latent space of neural shape generators that map latent codes
to 3D deformable shapes. The key focus is to look at a deformable shape generator from a …

For robots to work alongside humans and perform in unstructured environments, they must
learn new motion skills and adapt them to unseen situations on the fly. This demands …

In recent decades, advancements in motion learning have enabled robots to acquire new
skills and adapt to unseen conditions in both structured and unstructured environments. In …

Abstract Model-based offline reinforcement learning approaches generally rely on bounds of
model error. Estimating these bounds is usually achieved through uncertainty estimation …