Quaternion Quantum Neural Network for Classification

IF 1.1 2区数学 Q2 MATHEMATICS, APPLIED

Advances in Applied Clifford Algebras Pub Date : 2023-06-21 DOI:10.1007/s00006-023-01280-0

Guillermo Altamirano-Escobedo, Eduardo Bayro-Corrochano

引用次数: 1

Abstract

We propose the quaternionic quantum neural network (QQNN) for pattern recognition based on the formulation of quaternionic qubits and the construction of activation operators. In this model, the inputs and targets are represented by quaternionic qubits. The proposed neural network is evaluated through a series of experiments using different benchmark datasets, where the results show its superiority as a classifier in terms of accuracy when it is compared to conventional (real-valued) neural networks.

Abstract Image

查看原文本刊更多论文

用于分类的四元数量子神经网络

基于四元数量子位的公式和激活算子的构造，我们提出了用于模式识别的四元数量子神经网络（QQNN）。在这个模型中，输入和目标由四元数量子位表示。使用不同的基准数据集，通过一系列实验对所提出的神经网络进行了评估，结果表明，与传统（实值）神经网络相比，该网络在准确性方面具有优越性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Advances in Applied Clifford Algebras 数学-物理：数学物理

CiteScore

2.20

自引率

13.30%

发文量

审稿时长

3 months

期刊介绍： Advances in Applied Clifford Algebras (AACA) publishes high-quality peer-reviewed research papers as well as expository and survey articles in the area of Clifford algebras and their applications to other branches of mathematics, physics, engineering, and related fields. The journal ensures rapid publication and is organized in six sections: Analysis, Differential Geometry and Dirac Operators, Mathematical Structures, Theoretical and Mathematical Physics, Applications, and Book Reviews.