TY - GEN
T1 - Comparing Concepts of Quantum and Classical Neural Network Models for Image Classification Task
AU - Potempa, Rafał
AU - Porebski, Sebastian
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - 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).
AB - 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).
KW - Image recognition
KW - Quantum circuit
KW - Quantum computing
KW - Quantum data representation
KW - Quantum neural network
UR - https://www.scopus.com/pages/publications/85115150573
U2 - 10.1007/978-3-030-81523-3_6
DO - 10.1007/978-3-030-81523-3_6
M3 - Conference contribution
AN - SCOPUS:85115150573
SN - 9783030815226
T3 - Lecture Notes in Networks and Systems
SP - 61
EP - 71
BT - Progress in Image Processing, Pattern Recognition and Communication Systems - Proceedings of the Conference CORES, IP and C, ACS 2021
A2 - Choras, Michal
A2 - Choras, Ryszard S.
A2 - Kurzyński, Marek
A2 - Trajdos, Paweł
A2 - Pejas, Jerzy
A2 - Hyla, Tomasz
PB - Springer Science and Business Media Deutschland GmbH
T2 - International 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
Y2 - 28 June 2021 through 30 June 2021
ER -