DeepLog: A Software Framework for Modular Neurosymbolic AI
Abstract
DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic systems focus on a particular paradigm and semantics, DeepLog serves as a universal backend that can emulate many systems in the neurosymbolic alphabet soup. By treating diverse neurosymbolic languages as high-level specifications, the DeepLog software automatically compiles them into optimized arithmetic circuits. This design lowers the barrier for machine learning practitioners by treating logic as composable modules, while providing neurosymbolic developers with a shared, high-performance basis for prototyping new integration strategies. The code is available here: https://github.com/ML-KULeuven/deeplog
Cite
@article{arxiv.2605.10279,
title = {DeepLog: A Software Framework for Modular Neurosymbolic AI},
author = {Robin Manhaeve and Stefano Colamonaco and Vincent Derkinderen and Rik Adriaensen and Lucas Van Praet and Luc De Raedt and Giuseppe Marra},
journal= {arXiv preprint arXiv:2605.10279},
year = {2026}
}
Comments
Preprint accepted at IJCAI2026 Demo Track