Learning Signal Temporal Logic through Neural Network for Interpretable Classification

10/04/2022
by   Danyang Li, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/24/2019

Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques

Cyber-physical system applications such as autonomous vehicles, wearable...
research
09/15/2022

Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Description

Most existing Time series classification (TSC) models lack interpretabil...
research
04/08/2021

Neural Network for Weighted Signal Temporal Logic

In this paper, we propose a neuro-symbolic framework called weighted Sig...
research
10/01/2021

Classification of Time-Series Data Using Boosted Decision Trees

Time-series data classification is central to the analysis and control o...
research
05/24/2021

Inferring Temporal Logic Properties from Data using Boosted Decision Trees

Many autonomous systems, such as robots and self-driving cars, involve r...
research
12/28/2021

Time-Incremental Learning from Data Using Temporal Logics

Real-time and human-interpretable decision-making in cyber-physical syst...
research
05/08/2023

Exploring a Gradient-based Explainable AI Technique for Time-Series Data: A Case Study of Assessing Stroke Rehabilitation Exercises

Explainable artificial intelligence (AI) techniques are increasingly bei...

Please sign up or login with your details

Forgot password? Click here to reset