Exploiting Dual-Gate Ambipolar CNFETs for Scalable Machine Learning Classification

TL;DR

This paper presents a novel mixed-signal machine learning classifier using ambipolar CNFETs, demonstrating high accuracy, low power, and compact size for scalable hardware implementations.

Contribution

It introduces a new ML classifier design based on AP-CNFETs, leveraging their unique properties for improved performance and integration.

Findings

Achieved 90% accuracy on MNIST dataset

Demonstrated lower power consumption than CMOS and memristor classifiers

System operates at 250 MHz with a 15 nm feature size

Abstract

Ambipolar carbon nanotube based field-effect transistors (AP-CNFETs) exhibit unique electrical characteristics, such as tri-state operation and bi-directionality, enabling systems with complex and reconfigurable computing. In this paper, AP-CNFETs are used to design a mixed-signal machine learning (ML) classifier. The classifier is designed in SPICE with feature size of 15 nm and operates at 250 MHz. The system is demonstrated based on MNIST digit dataset, yielding 90% accuracy and no accuracy degradation as compared with the classification of this dataset in Python. The system also exhibits lower power consumption and smaller physical size as compared with the state-of-the-art CMOS and memristor based mixed-signal classifiers.