The overall goal of neuro-symbolic computation is to integrate high-level reasoning with low-level perception. We argue 1) that neuro-symbolic computation should integrate neural networks with the two most prominent methods for reasoning, that is, logic and probability, and 2) that neuro-symbolic integrated methods should have the pure neural, logical and probabilistic methods as special cases. We examine the state-of-the-art with regard to these claims and briefly position our own contribution DeepProbLog in this perspective.

As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.

Recent advances in causal reasoning have given rise to a computation model that emulates the process by which humans generate, evaluate and distinguish counterfactual sentences. Though compatible with the “possible worlds” account, this model enjoys the advantages of representational economy, algorithmic simplicity and conceptual clarity. Using this model, the paper demonstrates the processing of counterfactual sentences on a classical example due to Ernest Adam. It then gives a panoramic view of several applications where counterfactual reasoning has benefited problem areas in the empirical sciences.