Performance Evaluation of CMOS Annealing with Support Vector Machine

TL;DR

This study evaluates the performance of support vector machines on a quantum-inspired CMOS annealer, demonstrating comparable accuracy to classical computation in binary classification tasks.

Contribution

It introduces the use of a CMOS annealer for SVM performance evaluation, providing comparative accuracy analysis with classical CPU-based SVM.

Findings

CMOS annealer achieves 93.7% accuracy on linearly separable problems.

Accuracy of 92.7% and 97.6% on two non-linearly separable problems.

CMOS annealer's performance closely rivals classical SVM computation.

Abstract

In this paper, support vector machine (SVM) performance was assessed utilizing a quantum-inspired complementary metal-oxide semiconductor (CMOS) annealer. The primary focus during performance evaluation was the accuracy rate in binary classification problems. A comparative analysis was conducted between SVM running on a CPU (classical computation) and executed on a quantum-inspired annealer. The performance outcome was evaluated using a CMOS annealing machine, thereby obtaining an accuracy rate of 93.7% for linearly separable problems, 92.7% for non-linearly separable problem 1, and 97.6% for non-linearly separable problem 2. These results reveal that a CMOS annealing machine can achieve an accuracy rate that closely rivals that of classical computation.