Making Logic Learnable With Neural Networks

TL;DR

This paper introduces a pipeline that converts neural network models into logic circuits through intermediate steps, enhancing interpretability, verifiability, and hardware efficiency while maintaining high accuracy, demonstrated on biomedical data.

Contribution

It presents a novel method combining neural networks, random forests, and logic circuits for learnable, hardware-implementable, and interpretable models.

Findings

Greater accuracy than naive logic translation

Reduced hardware cost due to minimized logic

Effective application on biomedical data for clinical decision support

Abstract

While neural networks are good at learning unspecified functions from training samples, they cannot be directly implemented in hardware and are often not interpretable or formally verifiable. On the other hand, logic circuits are implementable, verifiable, and interpretable but are not able to learn from training data in a generalizable way. We propose a novel logic learning pipeline that combines the advantages of neural networks and logic circuits. Our pipeline first trains a neural network on a classification task, and then translates this, first to random forests, and then to AND-Inverter logic. We show that our pipeline maintains greater accuracy than naive translations to logic, and minimizes the logic such that it is more interpretable and has decreased hardware cost. We show the utility of our pipeline on a network that is trained on biomedical data. This approach could be applied to patient care to provide risk stratification and guide clinical decision-making.