Abstract:
We demonstrate the first recurrent neural network architecture for learning signal temporal logic (TL) formulas, and present the first systematic comparison of formula in...Show MoreMetadata
Abstract:
We demonstrate the first recurrent neural network architecture for learning signal temporal logic (TL) formulas, and present the first systematic comparison of formula inference methods. Legacy systems embed much expert knowledge which is not explicitly formalized. There is great interest in learning formal specifications that characterize the ideal behavior of such systems—that is, formulas in TL that are satisfied by the system’s output signals. Such specifications can be used to better understand the system’s behavior and improve the design of its next iteration. Previous inference methods either assumed certain formula templates, or did a heuristic enumeration of all possible templates. This work proposes a neural network architecture that infers the formula structure via gradient descent, eliminating the need for imposing any specific templates. It combines the learning of formula structure and parameters in one optimization. Through systematic comparison, we demonstrate that this method achieves similar or better misclassification rates (MCRs) than enumerative and lattice methods. We also observe that different formulas can achieve similar MCR, empirically demonstrating the under-determinism of the problem of TL inference.
Published in: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems ( Volume: 41, Issue: 11, November 2022)