TY - GEN
T1 - Quantum Convolutional Neural Network for Resource-Efficient Image Classification
T2 - 35th International Conference on Information Networking, ICOIN 2021
AU - Oh, Seunghyeok
AU - Choi, Jaeho
AU - Kim, Jong Kook
AU - Kim, Joongheon
N1 - Funding Information:
ACKNOWLEDGMENT This research was supported by National Research Foundation of Korea (2019M3E4A1080391). J. Kim is a corresponding author (e-mail: joongheon@korea.ac.kr).
Publisher Copyright:
© 2021 IEEE.
PY - 2021/1/13
Y1 - 2021/1/13
N2 - Convolutional Neural Network (CNN) is a breakthrough learning model that shows outstanding performance in computer vision and deep learning applications. However, it is a relatively burdened model in terms of learning speed and resource usage compared to other learning models when the learning scale becomes large. Quantum Convolutional Neural Network (QCNN) is a novel model as a potential solution using quantum computers to handle this problem. Quantum computers with a limited number of usable qubits needs a resource-efficient method to process large-scale data at once. In addition, Quantum Random Access Memory (QRAM) can store the large data to qubits logarithmically using superposition and entanglement. The QRAM algorithm can design a new QCNN model that can efficiently process in massive data. This paper proposes a more resource and depth efficient model for larger-sized input data and the number of output channels using the QRAM algorithm and efficiently extracting features.
AB - Convolutional Neural Network (CNN) is a breakthrough learning model that shows outstanding performance in computer vision and deep learning applications. However, it is a relatively burdened model in terms of learning speed and resource usage compared to other learning models when the learning scale becomes large. Quantum Convolutional Neural Network (QCNN) is a novel model as a potential solution using quantum computers to handle this problem. Quantum computers with a limited number of usable qubits needs a resource-efficient method to process large-scale data at once. In addition, Quantum Random Access Memory (QRAM) can store the large data to qubits logarithmically using superposition and entanglement. The QRAM algorithm can design a new QCNN model that can efficiently process in massive data. This paper proposes a more resource and depth efficient model for larger-sized input data and the number of output channels using the QRAM algorithm and efficiently extracting features.
UR - http://www.scopus.com/inward/record.url?scp=85100798148&partnerID=8YFLogxK
U2 - 10.1109/ICOIN50884.2021.9333906
DO - 10.1109/ICOIN50884.2021.9333906
M3 - Conference contribution
AN - SCOPUS:85100798148
T3 - International Conference on Information Networking
SP - 50
EP - 52
BT - 35th International Conference on Information Networking, ICOIN 2021
PB - IEEE Computer Society
Y2 - 13 January 2021 through 16 January 2021
ER -