Skip to main navigation Skip to search Skip to main content

Comparing Concepts of Quantum and Classical Neural Network Models for Image Classification Task

  • Rafał Potempa
  • , Sebastian Porebski
  • Silesian University of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Citations (Scopus)

Abstract

While quantum architectures are still under development, when available, they will only be able to process quantum data when machine learning algorithms can only process numerical data. Therefore, in the issues of classification or regression, it is necessary to simulate and study quantum systems that will transfer the numerical input data to a quantum form and enable quantum computers to use the available methods of machine learning. This material includes the results of experiments on training and performance of a hybrid quantum-classical neural network developed for the problem of classification of handwritten digits from the MNIST data set. The comparative results of two models: classical and quantum neural networks of a similar number of training parameters, indicate that the quantum network, although its simulation is time-consuming, overcomes the classical network (it has better convergence and achieves higher training and testing accuracy).

Original languageEnglish
Title of host publicationProgress in Image Processing, Pattern Recognition and Communication Systems - Proceedings of the Conference CORES, IP and C, ACS 2021
EditorsMichal Choras, Ryszard S. Choras, Marek Kurzyński, Paweł Trajdos, Jerzy Pejas, Tomasz Hyla
PublisherSpringer Science and Business Media Deutschland GmbH
Pages61-71
Number of pages11
ISBN (Print)9783030815226
DOIs
Publication statusPublished - 2022
EventInternational Conference on Image Processing and Communications, IPandC 2021, International Conference on Computer Recognition Systems, CORES 2021 and International Conference on Advanced Computer Systems, ACS 2021 - Virtual, Online
Duration: 28 Jun 202130 Jun 2021

Publication series

NameLecture Notes in Networks and Systems
Volume255
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceInternational Conference on Image Processing and Communications, IPandC 2021, International Conference on Computer Recognition Systems, CORES 2021 and International Conference on Advanced Computer Systems, ACS 2021
CityVirtual, Online
Period28/06/2130/06/21

Keywords

  • Image recognition
  • Quantum circuit
  • Quantum computing
  • Quantum data representation
  • Quantum neural network

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Comparing Concepts of Quantum and Classical Neural Network Models for Image Classification Task'. Together they form a unique fingerprint.

Cite this