AutoQML: Automatic generation and training of robust quantum-inspired classifiers by using evolutionary algorithms on grayscale images

A new hybrid system is proposed for automatically generating and training quantum-inspired classifiers on grayscale images by using multiobjective genetic algorithms. It is defined a dynamic fitness function to obtain the smallest circuit complexity and highest accuracy on unseen data, ensuring that...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications Vol. 244; p. 122984
Main Authors: Altares-López, Sergio, García-Ripoll, Juan José, Ribeiro, Angela
Format: Journal Article
Language:English
Published: Elsevier Ltd 15.06.2024
Subjects:
Automatic quantum circuit generation
Evolutionary algorithms
Image classification
Quantum artificial intelligence
Quantum kernel methods
Quantum-inspired machine learning
Automatic quantum circuit generation
Quantum kernel methods
Quantum-inspired machine learning
Evolutionary algorithms
Quantum artificial intelligence
Image classification
ISSN:0957-4174, 1873-6793
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new hybrid system is proposed for automatically generating and training quantum-inspired classifiers on grayscale images by using multiobjective genetic algorithms. It is defined a dynamic fitness function to obtain the smallest circuit complexity and highest accuracy on unseen data, ensuring that the proposed technique is generalizable and robust. At the same time, it is minimized the complexity of the generated circuits in terms of the number of entangling operators by penalizing their appearance and number of gates. The size of the images is reduced by using two dimensionality reduction approaches: principal component analysis (PCA), which is encoded within the individual and genetically optimized by the system, and a small convolutional autoencoder (CAE). These two methods are compared with one another and with a classical nonlinear approach to understand their behaviors and to ensure that the classification ability is due to the quantum circuit and not the preprocessing technique used for dimensionality reduction. •AutoQML: an automatic tool for generating and training quantum classifiers.•Complexity and accuracy optimization using multi-objective genetic algorithms.•Application of quantum systems in high-dimensional data such as grayscale images.•Comparison among dimensionality reduction methods for QML and a classical system.•Improved classification by coding the dimensionality reduction method in individual.
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2023.122984