DeepLog: A Software Framework for Modular Neurosymbolic AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Manhaeve, Robin, Colamonaco, Stefano, Derkinderen, Vincent, Adriaensen, Rik, Van Praet, Lucas, De Raedt, Luc, Marra, Giuseppe
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917480005369856
author Manhaeve, Robin
Colamonaco, Stefano
Derkinderen, Vincent
Adriaensen, Rik
Van Praet, Lucas
De Raedt, Luc
Marra, Giuseppe
author_facet Manhaeve, Robin
Colamonaco, Stefano
Derkinderen, Vincent
Adriaensen, Rik
Van Praet, Lucas
De Raedt, Luc
Marra, Giuseppe
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2605_10279
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DeepLog: A Software Framework for Modular Neurosymbolic AI
Manhaeve, Robin
Colamonaco, Stefano
Derkinderen, Vincent
Adriaensen, Rik
Van Praet, Lucas
De Raedt, Luc
Marra, Giuseppe
Machine Learning
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
title DeepLog: A Software Framework for Modular Neurosymbolic AI
topic Machine Learning
url https://arxiv.org/abs/2605.10279