TY  - JOUR
T1  - Effect of Gate Variations on MNIST Classification in QNN: Experimental Study and Analysis
AU  - Son, Seok Bin 
AU  - Baek, Hankyul 
AU  - Park, Soohyun 
JO  - The Journal of Korean Institute of Communications and Information Sciences
PY  - 2024
DA  - 2024/1/1
DO  - 10.7840/kics.2024.49.2.254
KW  - QNN
KW  - Gate variation
KW  - Quantum gate
KW  - PQC
KW  - MNIST
AB  - Recently, QNNs have emerged as a promising method for big data processing because they can process data at high speeds while using fewer parameters than existing machine learning algorithms. In the structure of QNN, the performance is determined by which quantum gates are used in the PQC, which constitutes the quantum circuit. Therefore, we conduct a performance comparison experiment in this paper using various quantum gates in QNNs. Through four comparison experiments using the MNIST dataset, we confirm that performance differences occur depending on the use of gates in QNNs and discuss the reasons for the performance differences. Therefore, in this paper, we verify that the performance of QNNs varies depending on the quantum gate variation.