Deep Differentiable Logic Gate Networks

TL;DR

This paper introduces differentiable logic gate networks that combine real-valued logic with a continuous relaxation, enabling fast inference and effective training via gradient descent for machine learning tasks.

Contribution

The authors propose a novel differentiable architecture for logic gate networks, allowing gradient-based training and fast inference speeds.

Findings

Achieved over a million images per second inference on MNIST.

Enabled effective training of logic gate networks with gradient descent.

Demonstrated fast execution speeds suitable for real-time applications.

Abstract

Recently, research has increasingly focused on developing efficient neural network architectures. In this work, we explore logic gate networks for machine learning tasks by learning combinations of logic gates. These networks comprise logic gates such as "AND" and "XOR", which allow for very fast execution. The difficulty in learning logic gate networks is that they are conventionally non-differentiable and therefore do not allow training with gradient descent. Thus, to allow for effective training, we propose differentiable logic gate networks, an architecture that combines real-valued logics and a continuously parameterized relaxation of the network. The resulting discretized logic gate networks achieve fast inference speeds, e.g., beyond a million images of MNIST per second on a single CPU core.