DeepLog: A Software Framework for Modular Neurosymbolic AI
2026-05-11 • Machine Learning
Machine Learning
AI summaryⓘ
The authors present DeepLog, a tool that combines logical reasoning and deep learning into one system using PyTorch. Instead of focusing on just one style, DeepLog can mimic many existing neurosymbolic methods by converting them into efficient math circuits automatically. This helps both machine learning users by making logic easier to use, and researchers by giving them a common platform to build new techniques. The code for DeepLog is publicly available for others to try.
neurosymbolic systemsdeep learninglogic programmingPyTorcharithmetic circuitsmachine learningcompilationmodularityprototyping
Authors
Robin Manhaeve, Stefano Colamonaco, Vincent Derkinderen, Rik Adriaensen, Lucas Van Praet, Luc De Raedt, Giuseppe Marra
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