Year: 2021
Type: preprint
Abstract: Finite linear temporal logic ($\mathsf{LTL}_f$) is a powerful formal representation for modeling temporal sequences. We address the problem of learning a compact $\mathsf{LTL}_f$ formula from labeled traces of system behavior. We propose a novel neural network operator and evaluate the resulting architecture, Neural$\mathsf{LTL}_f$. Our approach includes a specialized recurrent filter, designed to subsume $\mathsf{LTL}_f$ temporal operators, to learn a highly accurate classifier for traces. Then, it discretizes the activations and extracts the truth table represented by the learned weights. This truth table is converted to symbolic form and returned as the learned formula. Experiments on randomly generated $\mathsf{LTL}_f$ formulas show Neural$\mathsf{LTL}_f$ scales to larger formula sizes than existing approaches and maintains high accuracy even in the presence of noise.
Source: arXiv (Cornell University)
Authors: Walke, Homer, Ritter, Daniel, Trimbach, Carl, Littman, Michael
Institutions: Brown University, University of California, Berkeley
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3214220002