English

Learning Signal Temporal Logic through Neural Network for Interpretable Classification

Formal Languages and Automata Theory 2023-07-04 v2 Machine Learning

Abstract

Machine learning techniques using neural networks have achieved promising success for time-series data classification. However, the models that they produce are challenging to verify and interpret. In this paper, we propose an explainable neural-symbolic framework for the classification of time-series behaviors. In particular, we use an expressive formal language, namely Signal Temporal Logic (STL), to constrain the search of the computation graph for a neural network. We design a novel time function and sparse softmax function to improve the soundness and precision of the neural-STL framework. As a result, we can efficiently learn a compact STL formula for the classification of time-series data through off-the-shelf gradient-based tools. We demonstrate the computational efficiency, compactness, and interpretability of the proposed method through driving scenarios and naval surveillance case studies, compared with state-of-the-art baselines.

Keywords

Cite

@article{arxiv.2210.01910,
  title  = {Learning Signal Temporal Logic through Neural Network for Interpretable Classification},
  author = {Danyang Li and Mingyu Cai and Cristian-Ioan Vasile and Roberto Tron},
  journal= {arXiv preprint arXiv:2210.01910},
  year   = {2023}
}
R2 v1 2026-06-28T02:48:48.991Z