Abstract Develo** Deep Convolutional Neural Networks (DCNNs) for image classification
is a complicated task that needs considerable effort and knowledge. By employing an …

Deep neural networks (DNNs) are the workhorses of deep learning, which constitutes the
state of the art in numerous application domains. However, DNN-based decision rules are …

Increasingly sophisticated mathematical modelling processes from Machine Learning are
being used to analyse complex data. However, the performance and explainability of these …

Probabilistic programming languages are used to write probabilistic models to make
probabilistic inferences. A number of rigorous semantics have recently been proposed that …

Verification of neural networks relies on activation functions being piecewise affine (pwa)—
enabling an encoding of the verification problem for theorem provers. In this paper, we …

Neural networks are increasingly being moved to edge computing devices and smart
sensors, to reduce latency and save bandwidth. Neural network compression such as …

Reinforcement learning algorithms solve sequential decision-making problems in
probabilistic environments by optimizing for long-term reward. The desire to use …

For performance and verification in machine learning, new methods have recently been
proposed that optimise learning systems to satisfy formally expressed logical properties …

We formally verify executable algorithms for solving Markov decision processes (MDPs) in
the interactive theorem prover Isabelle/HOL. We build on existing formalizations of …

Neuro-symbolic programs--programs containing both machine learning components and
traditional symbolic code--are becoming increasingly widespread. However, we believe that …