Discovering interpretable patterns for classification of sequential data is of key importance for a variety of fields, ranging from genomics to fraud detection or more generally interpretable decision-making. In this paper, we propose a novel differentiable fully interpretable method to discover both local and global patterns (i.e. It consists of a convolutional binary neural network with an interpretable neural filter and a training strategy based on dynamically-enforced sparsity. We demonstrate the validity and usefulness of the approach on synthetic datasets and on an open-source peptides dataset. Key to this end-to-end differentiable method is that the expressive patterns used in the rules are learned alongside the rules themselves. During the last decades, machine learning and in particular neural networks have made tremendous progress on classification tasks for a variety of fields such as healthcare, fraud detection or entertainment. They are able to learn from various data types ranging from images to timeseries and achieve impressive classification accuracy. However, they are difficult or impossible to understand by a human.

Widely adopted for more than 20 years in industrial fields, business rules offer the opportunity to non-IT users to define decision-making policies in a simple and intuitive way. When used conjointly with probabilistic graphical models (PGM) their expressiveness increase by introducing the notion of probabilistic production rules (PPR). In this paper we will present a new model for PPR and suggest a way to handle the combinatorial explosion due to the number of parents of aggregators in PGM such as Bayesian Networks and Probabilistic Relational Models in an industrial context where marginals should be computed rapidly.