Recognition of Continuous Digits by Quantum Neural Networks

作     者：LI Fei, ZHAO Sheng-mei, ZHENG Bao-yu (Institute of Signal & Information Processing, Nanjing University of Posts and Telecommunications, Nanjing 210003, P.R. China) 

作者机构：Institute of Signal & Information Processing Nanjing University of Posts and Telecommunications Nanjing 210003 

出 版 物：《The Journal of China Universities of Posts and Telecommunications》 (中国邮电高校学报（英文版）)

年 卷 期：2003年第10卷第1期

页      面：29-33页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：theScienceandTechnologyFoundationoftheEducationDepartmentofJiangsuProvince (No.2 0 0 1 1 9) 

主　　题：quantum neural net-work quantum neuron speech recognition 

摘      要：This paper describes a new kind of neural network-Quantum Neural Network(QNN) and its application to recognition of continuous digits. QNN combines the advantages of neuralmodeling and fuzzy theoretic principles . Experiment results show that more than 15 percent errorreduction is achieved on a speaker-independent continuous digits recognition task compared with BPnetworks.