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

09/15/2022
by   Ruixuan Yan, et al.
0

Most existing Time series classification (TSC) models lack interpretability and are difficult to inspect. Interpretable machine learning models can aid in discovering patterns in data as well as give easy-to-understand insights to domain specialists. In this study, we present Neuro-Symbolic Time Series Classification (NSTSC), a neuro-symbolic model that leverages signal temporal logic (STL) and neural network (NN) to accomplish TSC tasks using multi-view data representation and expresses the model as a human-readable, interpretable formula. In NSTSC, each neuron is linked to a symbolic expression, i.e., an STL (sub)formula. The output of NSTSC is thus interpretable as an STL formula akin to natural language, describing temporal and logical relations hidden in the data. We propose an NSTSC-based classifier that adopts a decision-tree approach to learn formula structures and accomplish a multiclass TSC task. The proposed smooth activation functions for wSTL allow the model to be learned in an end-to-end fashion. We test NSTSC on a real-world wound healing dataset from mice and benchmark datasets from the UCR time-series repository, demonstrating that NSTSC achieves comparable performance with the state-of-the-art models. Furthermore, NSTSC can generate interpretable formulas that match with domain knowledge.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2021

Neural Network for Weighted Signal Temporal Logic

In this paper, we propose a neuro-symbolic framework called weighted Sig...
research
10/04/2022

Learning Signal Temporal Logic through Neural Network for Interpretable Classification

Machine learning techniques using neural networks have achieved promisin...
research
03/27/2013

Towards The Inductive Acquisition of Temporal Knowledge

The ability to predict the future in a given domain can be acquired by d...
research
07/24/2019

Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques

Cyber-physical system applications such as autonomous vehicles, wearable...
research
07/08/2022

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective

Classical medium access control (MAC) protocols are interpretable, yet t...
research
07/28/2023

Bayesian Time-Series Classifier for Decoding Simple Visual Stimuli from Intracranial Neural Activity

Understanding how external stimuli are encoded in distributed neural act...
research
04/11/2016

Reverse Engineering and Symbolic Knowledge Extraction on Łukasiewicz Fuzzy Logics using Linear Neural Networks

This work describes a methodology to combine logic-based systems and con...

Please sign up or login with your details

Forgot password? Click here to reset