Approximate Decision Trees For Machine Learning Classification on Tiny Printed Circuits

TL;DR

This paper develops approximate decision tree classifiers optimized for tiny, resource-constrained printed electronics, enabling machine learning applications in ultra-low-cost, flexible, and non-toxic printed circuits.

Contribution

It introduces a hardware-efficient approximation method for decision trees tailored for printed electronics, facilitating ML in ultra-resource-constrained environments.

Findings

Effective decision tree approximations for printed circuits.

Reduced resource usage enabling ML on tiny printed devices.

Potential for new applications in flexible electronics.

Abstract

Although Printed Electronics (PE) cannot compete with silicon-based systems in conventional evaluation metrics, e.g., integration density, area and performance, PE offers attractive properties such as on-demand ultra-low-cost fabrication, flexibility and non-toxicity. As a result, it targets application domains that are untouchable by lithography-based silicon electronics and thus have not yet seen much proliferation of computing. However, despite the attractive characteristics of PE, the large feature sizes in PE prohibit the realization of complex printed circuits, such as Machine Learning (ML) classifiers. In this work, we exploit the hardware-friendly nature of Decision Trees for machine learning classification and leverage the hardware-efficiency of the approximate design in order to generate approximate ML classifiers that are suitable for tiny, ultra-resource constrained, and battery-powered printed applications.