Quantum neural networks with deep residual learning

by   Yanying Liang, et al.

Inspired by the success of neural networks in the classical machine learning tasks, there has been tremendous effort to develop quantum neural networks (QNNs), especially for quantum data or tasks that are inherently quantum in nature. Currently, with the imminent advent of quantum computing processors to evade the computational and thermodynamic limitation of classical computations, designing an efficient quantum neural network becomes a valuable task in quantum machine learning. In this paper, a novel quantum neural network with deep residual learning (ResQNN) is proposed. Specifically, a multiple layer quantum perceptron with residual connection is provided. Our ResQNN is able to learn an unknown unitary and get remarkable performance. Besides, the model can be trained with an end-to-end fashion, as analogue of the backpropagation in the classical neural networks. To explore the effectiveness of our ResQNN , we perform extensive experiments on the quantum data under the setting of both clean and noisy training data. The experimental results show the robustness and superiority of our ResQNN, when compared to current remarkable work, which is from Nature communications, 2020. Moreover, when training with higher proportion of noisy data, the superiority of our ResQNN model can be even significant, which implies the generalization ability and the remarkable tolerance for noisy data of the proposed method.


page 1

page 2

page 3

page 4


Efficient Learning for Deep Quantum Neural Networks

Neural networks enjoy widespread success in both research and industry a...

Comparing concepts of quantum and classical neural network models for image classification task

While quantum architectures are still under development, when available,...

QDCNN: Quantum Dilated Convolutional Neural Network

In recent years, with rapid progress in the development of quantum techn...

QDNN: DNN with Quantum Neural Network Layers

The deep neural network (DNN) became the most important and powerful mac...

When Machine Learning Meets Quantum Computers: A Case Study

Along with the development of AI democratization, the machine learning a...

A Derivative-free Method for Quantum Perceptron Training in Multi-layered Neural Networks

In this paper, we present a gradient-free approach for training multi-la...

Quantum Transfer Learning for Wi-Fi Sensing

Beyond data communications, commercial-off-the-shelf Wi-Fi devices can b...