NeurIPS 2020

STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks

Meta Review

This paper initially received three reviews. The reviewers appreciated the integration of temporal logic with deep learning presented in the paper. The main concerns centered around the relations of the proposed method to existing literature and first-order logic specifications. After reading the authors' rebuttal the reviewers engaged in detailed debate around the merits of the paper. A fourth expert reviewer's opinion was sought to help come to a decision. In the end, it was determined that the merits of the paper outweigh the potential concerns. This is an interesting, important area of recent research and the paper will continue to spur interest in this direction. The authors are encouraged to modify the camera ready to: include further discussion regarding FOL vs. the proposed STL representation, the relation to previous work cited by the reviewers and particularly a thorough discussion with respect to [7].