Learning complex control policies from high-dimensional sensory input is a challenge for
reinforcement learning algorithms. Kernel methods that approximate values functions or …

We study the problem of predicting the future, though only in the probabilistic sense of
estimating a future state of a time-varying probability distribution. This is not only an …

Complicated generative models often result in a situation where computing the likelihood of
observed data is intractable, while simulating from the conditional density given a parameter …

Complicated generative models often result in a situation where computing the likelihood of
observed data is intractable, while simulating from the conditional density given a parameter …

The ability of a human being to extrapolate previously gained knowledge to other domains
inspired a new family of methods in machine learning called transfer learning. Transfer …

We propose to learn a kernel-based message operator which takes as input all expectation
propagation (EP) incoming messages to a factor node and produces an outgoing message …

In this paper we propose a framework for supervised and semi-supervised learning based
on reformulating the learning problem as a regularized Fredholm integral equation. Our …