DeepLog: A Software Framework for Modular Neurosymbolic AI
This framework lowers the barrier for ML practitioners to use neurosymbolic AI and provides a shared backend for developers, but it is primarily an engineering contribution rather than a novel paradigm.
DeepLog is a universal neurosymbolic framework that compiles diverse logic specifications into optimized arithmetic circuits within PyTorch, enabling modular integration of logic and deep learning for practitioners and developers.
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