Learning continually from non-stationary data streams is a long-standing goal and a
challenging problem in machine learning. Recently, we have witnessed a renewed and fast …

Abstract Machine learning development creates multiple new challenges that are not
present in a traditional software development lifecycle. These include keeping track of the …

We introduce a probability distribution, combined with an efficient sampling algorithm, for
weights and biases of fully-connected neural networks. In a supervised learning context, no …

Recovering a high-quality image from noisy indirect measurements is an important problem
with many applications. For such inverse problems, supervised deep convolutional neural …

High-dimensional time series are common in many domains. Since human cognition is not
optimized to work well in high-dimensional spaces, these areas could benefit from …

MLflow is a popular open source platform for managing ML development, including
experiment tracking, reproducibility, and deployment. In this paper, we discuss user …

The explorative and iterative nature of developing and operating ML applications leads to a
variety of artifacts, such as datasets, features, models, hyperparameters, metrics, software …

imitation provides open-source implementations of imitation and reward learning algorithms
in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imitation …

Combinatorial generalisation—the ability to understand and produce novel combinations of
familiar elements—is a core capacity of human intelligence that current AI systems struggle …

Recent research has shown that generative models with highly disentangled
representations fail to generalise to unseen combination of generative factor values. These …