The vast quantity of information brought by big data as well as the evolving computer
hardware encourages success stories in the machine learning community. In the …

This paper develops variational continual learning (VCL), a simple but general framework
for continual learning that fuses online variational inference (VI) and recent advances in …

We introduce a framework for Continual Learning (CL) based on Bayesian inference over
the function space rather than the parameters of a deep neural network. This method …

Nanoporous materials (NPMs) could be used to store, capture, and sense many different
gases. Given an adsorption task, we often wish to search a library of NPMs for the one with …

Gaussian processes (GPs) are flexible distributions over functions that enable highlevel
assumptions about unknown functions to be encoded in a parsimonious, flexible and …

Laser-plasma physics has developed rapidly over the past few decades as lasers have
become both more powerful and more widely available. Early experimental and numerical …

Many applications of classification methods not only require high accuracy but also reliable
estimation of predictive uncertainty. However, while many current classification frameworks …

A challenging problem in task-free continual learning is the online selection of a
representative replay memory from data streams. In this work, we investigate the online …

Sequential Bayesian inference over predictive functions is a natural framework for continual
learning from streams of data. However, applying it to neural networks has proved …

The safe operation of physical systems typically relies on high-quality models. Since a
continuous stream of data is generated during run-time, such models are often obtained …