arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.11286cs.LGcs.AI
收藏

基于神经网络的序列数据分类规则学习

Neural-based classification rule learning for sequential data

IBM France Lab(IBM法国实验室);Inria Saclay(法国国家信息与自动化研究所萨克雷分部);IBM Research(IBM研究院)

Marine Collery, Philippe Bonnard, François Fages, Remy Kusters

摘要:

发现序列数据分类的可解释模式对于从基因组学到欺诈检测或更一般的可解释决策的各种领域都至关重要。在本文中,我们提出了一种新的微分完全可解释的方法,发现本地和全球的模式(即捕捉相对或绝对的时间依赖性)基于规则的二进制分类。它由一个卷积二进制神经网络与一个可解释的神经过滤器和训练策略的基础上动态强制稀疏。我们证明了该方法在合成数据集和开源肽数据集上的有效性和实用性。这种端到端可区分方法的关键在于,规则中使用的表达模式是与规则本身一起学习的。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑