mlsanityData to 7 Oct 2026

Neural Network for Weighted Signal Temporal Logic

arXiv 2104.05435 ↗First posted 8 Apr 2021cs.LG cs.NEcited by 5

Not on the map. Why?

Abstract (arXiv)

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. Weighted Signal Temporal Logic (wSTL) formulas are recursively composed of subformulas that are combined using logical and temporal operators. The quantitative semantics of wSTL is defined such that the quantitative satisfaction of subformulas with higher weights has more influence on the quantitative satisfaction of the overall wSTL formula. In the wSTL-NN, each neuron corresponds to a wSTL subformula, and its output corresponds to the quantitative satisfaction of the formula. We use wSTL-NN to represent wSTL formulas as features to classify time series data. STL features are more explainable than those used in classical methods. The wSTL-NN is end-to-end differentiable, which allows learning of wSTL formulas to be done using back-propagation. To reduce the number of weights, we introduce two techniques to sparsify the wSTL-NN.We apply our framework to an occupancy detection time-series dataset to learn a classifier that predicts the occupancy status of an office room.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 11 of its 37 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

11 of 37 references.

References · 11

  1. 2018Deep learning for time series classification: a reviewcited by 575
  2. 2017End-to-End Differentiable Provingcited by 159
  3. 2020Logical Neural Networkscited by 118
  4. 2016Training Sparse Neural Networkscited by 73
  5. 2019Transfer of Temporal Logic Formulas in Reinforcement Learningcited by 31
  6. 2018STyLuS*: A Temporal Logic Optimal Control Synthesis Algorithm for Large-Scale Multi-Robot Systemscited by 24
  7. 2020Specifying User Preferences using Weighted Signal Temporal Logiccited by 22
  8. 2018Information-Guided Temporal Logic Inference with Prior Knowledgecited by 12
  9. 2020Event-Based Signal Temporal Logic Synthesis for Single and Multi-Robot Taskscited by 7
  10. 2021Barrier Function-based Collaborative Control of Multiple Robots under Signal Temporal Logic Taskscited by 3
  11. 2020Automatic Trajectory Synthesis for Real-Time Temporal Logiccited by 1

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 0; 2024: 1.

5 papers.

  1. 2022Learning Signal Temporal Logic through Neural Network for Interpretable Classificationcited by 10
  2. 2021Weighted Graph-Based Signal Temporal Logic Inference Using Neural Networkscited by 4
  3. 2022Learning Temporal Rules from Noisy Timeseries Datacited by 2
  4. 2024Multi-class Temporal Logic Neural Networkscited by 2
  5. 2021Time-Incremental Learning from Data Using Temporal Logicscited by 0