电子学报Issue(12)：2401-2408,8.DOI:10.3969/j.issn.0372-2112.2014.12.010
一种量子衍生神经网络模型算法及应用
Algorith m and Application of the Quantu m-Inspired Neu ral Network Model
摘要
Abstract
To enhance the approximation and generalization ability of classical artificial neural networks,a quantum-inspired neural network model,whose input of each dimension is a discrete sequence,is proposed .This model concludes three layers,in which the hidden layer consists of quantum-inspired neurons,and the output layer consists of common neurons .The quantum-in-spired neuron consists of the quantum rotation gates and the multi-qubits controlled-rotation gates .By using the information feedback of target qubit from output to input in multi-qubits controlled-rotation gate,the overall memory of input sequences is realized .The output of quantum-inspired neuron is obtained from the entanglements of multi-qubits in controlled-rotation gates .The learning algo-rithm is designed in detail according to the basic principles of quantum computation .The characteristics of input sequence can be ef-fectively obtained by way of“breadth”and“depth”.The simulation results show that,when the input nodes and the length of the sequence satisfy a certain relations,the proposed model is obviously superior to the common artificial neural networks .关键词
量子计算/量子旋转门/受控旋转门/量子神衍生经元/量子衍生神经网络Key words
quantum computation/quantum rotation gate/controlled-rotation gate/quantum-inspired neuron/quantum-in-spired neural networks分类
信息技术与安全科学引用本文复制引用
杨淑云,李盼池..一种量子衍生神经网络模型算法及应用[J].电子学报,2014,(12):2401-2408,8.基金项目
国家自然科学基金 （）
