Neural-based classification rule learning for sequential data

Autor:	Collery, Marine, Bonnard, Philippe, Fages, François, Kusters, Remy
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	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. Comment: Published as a conference paper at ICLR 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2302.11286 Zobrazit plný text záznamu View this record from Arxiv