Constrained Training of Neural Networks via Theorem Proving

M. Chevallier, M. Whyte, J.D. Fleuriot

Research output: Working paperPreprint

Abstract / Description of output

We introduce a theorem proving approach to the specification and generation of temporal logical constraints for training neural networks. We formalise a deep embedding of linear temporal logic over finite traces (LTLf) and an associated evaluation function characterising its semantics within the higher-order logic of the Isabelle theorem prover. We then proceed to formalise a loss function L that we formally prove to be sound, and differentiable to a function dL. We subsequently use Isabelle's automatic code generation mechanism to produce OCaml versions of LTLf, L and dL that we integrate with PyTorch via OCaml bindings for Python. We show that, when used for training in an existing deep learning framework for dynamic movement, our approach produces expected results for common movement specification patterns such as obstacle avoidance and patrolling. The distinctive benefit of our approach is the fully rigorous method for constrained training, eliminating many of the risks inherent to ad-hoc implementations of logical aspects directly in an "unsafe" programming language such as Python.
Original languageEnglish
Number of pages19
Publication statusPublished - 8 Jul 2022

Keywords / Materials (for Non-textual outputs)

  • Linear temporal logic
  • neural networks
  • theorem proving
  • Isabelle/HOL


Dive into the research topics of 'Constrained Training of Neural Networks via Theorem Proving'. Together they form a unique fingerprint.

Cite this