A hybrid quantum-classical neural network with deep residual learning.
Yanying Liang, Wei Peng, Zhu-Jun Zheng, Olli Silvén, Guoying Zhao
Author Information
Yanying Liang: Center for Machine Vision and Signal Analysis, University of Oulu, Oulu 90570, Finland; School of Mathematics, South China University of Technology, Guangzhou 510641, China. Electronic address: yanying.liang@oulu.fi.
Wei Peng: Center for Machine Vision and Signal Analysis, University of Oulu, Oulu 90570, Finland.
Zhu-Jun Zheng: School of Mathematics, South China University of Technology, Guangzhou 510641, China; Laboratory of Quantum Science and Engineering, South China University of Technology, Guangzhou 510641, China.
Olli Silvén: Center for Machine Vision and Signal Analysis, University of Oulu, Oulu 90570, Finland.
Guoying Zhao: Center for Machine Vision and Signal Analysis, University of Oulu, Oulu 90570, Finland.
Inspired by the success of classical neural networks, there has been tremendous effort to develop classical effective neural networks into quantum concept. In this paper, a novel hybrid quantum-classical neural network with deep residual learning (Res-HQCNN) is proposed. We firstly analyse how to connect residual block structure with a quantum neural network, and give the corresponding training algorithm. At the same time, the advantages and disadvantages of transforming deep residual learning into quantum concept are provided. As a result, the model can be trained in an end-to-end fashion, analogue to the backpropagation in classical neural networks. To explore the effectiveness of Res-HQCNN , we perform extensive experiments for quantum data with or without noisy on classical computer. The experimental results show the Res-HQCNN performs better to learn an unknown unitary transformation and has stronger robustness for noisy data, when compared to state of the arts. Moreover, the possible methods of combining residual learning with quantum neural networks are also discussed.
