extreme machines for classification

A. De Lorenzis

doi:10.1103/PhysRevApplied.23.044024

extreme machines for classification

2025-04-09

0

PRE

AI

DOI：10.1103/PhysRevApplied.23.044024

原文链接

原文求助

摘要

En 中文

Interest in quantum machine learning is growing due to its potential to offer more efficient solutions for problems that are difficult to tackle with classical methods. In this context, the research work presented here focuses on the use of quantum machine-learning techniques for image-classification tasks. We exploit a quantum extreme learning machine by taking advantage of its rich feature map provided by the quantum reservoir substrate. We systematically analyze different phases of the quantum extreme learning machine process, from dataset preparation to final image classification. In particular, we test different encodings, together with principal component analysis and the use of autoencoders, and we examine the dynamics of the model through the use of different Hamiltonians for the quantum reservoir. Our results show that the introduction of a quantum reservoir systematically improves the accuracy of the classifier. In addition, our findings indicate that variations in encoding methods can significantly influence performance and that Hamiltonians with distinct structures exhibit the same discrimination rate, depending on how their eigenstates are related to the encoding and measurement basis.

Keyword:

PYTHON FRAMEWORK

QUANTUM

DYNAMICS

QUTIP

extreme machines for classification

摘要

期刊

机构

引用论文