Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Neural-based classification rule learning for sequential data

Marine Collery · Philippe Bonnard · François Fages · Remy Kusters

MH1-2-3-4 #159

Keywords: [ sequential data ] [ interpretable AI ] [ binary neural network ] [ classification rule learning ] [ Social Aspects of Machine Learning ]


Abstract:

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. catching a relative or absolute temporal dependency) for rule-based binary classification.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.

Chat is not available.