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

no code implementations • 15 Sep 2022 • Ruixuan Yan, Tengfei Ma, Achille Fokoue, Maria Chang, Agung Julius

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.

Interpretable Machine Learning Time Series +2

Weighted Graph-Based Signal Temporal Logic Inference Using Neural Networks

no code implementations • 16 Sep 2021 • Nasim Baharisangari, Kazuma Hirota, Ruixuan Yan, Agung Julius, Zhe Xu

It is important that the obtained knowledge is human-interpretable and amenable to formal analysis.

Classification

Neural Network for Weighted Signal Temporal Logic

no code implementations • 8 Apr 2021 • Ruixuan Yan, Agung Julius

In this paper, we propose a neuro-symbolic framework called weighted Signal Temporal Logic Neural Network (wSTL-NN) that combines the characteristics of neural networks and temporal logics.

Time Series Time Series Analysis