[1]朱 红,陈清华,刘国岁.高速神经网络HS-K-WTA-2的研究[J].南京理工大学学报(自然科学版),2007,(01):89-91.
 ZHU Hong,CHEN Qing-hua,LIU Guo-sui.High-speed Neural Network HS-K-WTA-2[J].Journal of Nanjing University of Science and Technology,2007,(01):89-91.
点击复制

高速神经网络HS-K-WTA-2的研究
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
期数:
2007年01期
页码:
89-91
栏目:
出版日期:
2007-02-28

文章信息/Info

Title:
High-speed Neural Network HS-K-WTA-2
作者:
朱 红 1 陈清华 2 刘国岁 1
南京理工大学 1. 电子工程与光电技术学院, 江苏 南京 210094; 2. 计算机科学与技术学院, 江苏 南京 210094
Author(s):
ZHU Hong1CHEN Qing-hua2LIU Guo-sui1
1.School of Electronic Engineering and Optoelectronic Technology,NUST,Nanjing 210094,China;2.School of Computer Science and Engineering,NUST,Nanjing 210094,China
关键词:
神经网络 竞争学习算法 高速算法 选择 K个较大数 K-WTA HS-K-WTA HS-K-WTA-2
Keywords:
neural network competitive learning algorithm high-speed algorithm K-WTA HS- K-WTA HS-K-WTA-2
分类号:
TP183
摘要:
该文提出了一种新的K-Winners-Take-All神经网络:High-Speed-K-Winners-Take-All-2(HS-K-WTA-2)。HS-K-WTA-2以竞争学习算法为基础。HS-K-WTA-2能够从任何一个数集中识别出K个较大的数,或K个较小的数。该文给出HS-K-WTA-2算法及算法复杂度的分析结果。用专门为研究K-WTA神经网络开发的仿真程序对HS-K-WTA-2、HS-K-WTA和Winstrons进行仿真研究。结果显示:当所取的数集N较大时,HS-K-WTA-2要比Winstrons和HS-K-WTA速度更快。HS-K-WTA-2的硬件实现比Winston的硬件实现要简单,比HS-K-WTA的硬件实现复杂。
Abstract:
A new K-W inners-T ake-All neural network: H igh-Speed-W inners-T ake-Al-l 2 ( HS-K- WTA-2) is presented. HS-K-WTA-2 can identify the larger elements ( or sm aller ones) in a data se.t The analysis results aboutHS-WTA-2 algorithm and its complexity are given. HS-K-WTA-2, HS-K-WTA andW instrons are simulated w ith a specific design simulation tool software forK-WTA neural network. The results show that the speed ofHS-K-WTA-2 ismuch quicker than W instrons andHS-K-WTA for a data setN that has a lot of atoms. H ardware implementention ofHS-K-WTA- 2 is simpler thanW instrons, and more complicated thanHS-K-WTA.

参考文献/References:

[ 1] Yen J C, Chang F J, Chang S. A newW inners-Take-A ll architecture in artificial neural network [ J]. IEEE Transactions onNeuralNetwork, 1994, 5(5): 838- 843.
[ 2] Yen J C, Guo J I, Chen H C. K-W inners-Take-A ll circuitw ithO (N ) complexity [ J]. IEEE Transactions on NeuralN etwork, 1995, 6 ( 6): 776- 778.
[ 3] Yen J C, Guo J I, Chen H C. A new K-W inners- Take-A ll neural network and its array architecture [ J]. IEEE Transactions on NeuralNetwork, 1998, 9 ( 5): 901- 912.
[ 4] 陈清华, 朱红, 杨静宇. 一种高速神经网络 HS-K- WTA的算法研究. 南京理工大学学 报, 2001, 25 (6): 669- 672.
[ 5] 朱红, 陈清华, 刘国岁. 一种高速神经网络 HS-K- WTA的研究 [ J]. 电子学报, 2002, 30( 7): 1 020- 1 022.

相似文献/References:

[1]何春梅,叶征春,韩牟,等.形态双向联想记忆网络的摄动鲁棒性研究[J].南京理工大学学报(自然科学版),2011,(05):664.
 HE Chun-mei,YE Zheng-chun,HAN Mu,et al.Perturbation Robustness of Morphological Bidirectional Associative Memories Networks[J].Journal of Nanjing University of Science and Technology,2011,(01):664.
[2]刘永建,朱剑英,曾捷,等.改进BP神经网络在发动机性能趋势分析和故障诊断中的应用[J].南京理工大学学报(自然科学版),2010,(01):24.
 LIU Yong-jian,ZHU Jian-ying,ZENG Jie.Improved BP Neural Network System for Engine Performance Trend Analysis and Fault Diagnosis[J].Journal of Nanjing University of Science and Technology,2010,(01):24.
[3]黄俊,徐越兰.碳钢焊条熔敷金属力学性能非线性神经网络组合预测[J].南京理工大学学报(自然科学版),2012,36(05):800.
 HUANG Jun,XU Yue-lan.Nonlinear Combination Prediction of Mechanical Properties of CarbonSteel Electrode Deposited Metal Based on Neural Network[J].Journal of Nanjing University of Science and Technology,2012,36(01):800.
[4]袁军堂,夏玲玲,汪振华,等.灌胶结合面对数控机床动态性能影响研究[J].南京理工大学学报(自然科学版),2012,36(06):0.
 YUAN Jun tang,XIA Ling ling,WANG Zhen hua,et al.Impact of Glued Joint on Dynamic Characteristics of CNC Machine Tool[J].Journal of Nanjing University of Science and Technology,2012,36(01):0.
[5]都洪基,苏炜宏,邓烽.一种基于神经网络的谐波电流抑制方法[J].南京理工大学学报(自然科学版),2003,(01):28.
 DuHongji SuWeihong DengFeng.Adaptive Approach to Detection of the Harmonic Currents on Artificial Neural Network[J].Journal of Nanjing University of Science and Technology,2003,(01):28.
[6]魏荣,卢俊国,李军,等.α阶时延逆系统的小波神经网络实现[J].南京理工大学学报(自然科学版),2001,(04):342.
 WeiRong LuJunguo LiJun WangZhiquan.Realization of α-order Time-delay Inverse Systems Based on Wavelet Neural Networks[J].Journal of Nanjing University of Science and Technology,2001,(01):342.
[7]聂伟荣,朱继南,赵玉霞.基于改进BP网络的地震动信号目标识别[J].南京理工大学学报(自然科学版),2000,(01):20.
 NieWeirong ZhuJinan ZhaoYuxia.Microseismic Signal Targets Identification Based on Improved BP Neural Networks[J].Journal of Nanjing University of Science and Technology,2000,(01):20.
[8]卢云许,陆宝春,张世琪.切片平均分子量神经网络预测模型研究及应用[J].南京理工大学学报(自然科学版),2000,(02):139.
 LuYunxu LuBaochun ZhangShiqi.The Research and Application of Neural Network Predicting Model of Molecule Weight of Casting Slice Belt[J].Journal of Nanjing University of Science and Technology,2000,(01):139.
[9]牛玉刚,杨成梧,赵建丛.基于多步预测的PID型神经网络控制[J].南京理工大学学报(自然科学版),2000,(03):199.
 NiuYugang YangChengwu ZhaoJiancong.A PID-like Neural Network Control Based on Multi-step Prediction[J].Journal of Nanjing University of Science and Technology,2000,(01):199.
[10]赵启林,卓家寿,柳景春.BP网络的BP-G-S学习算法[J].南京理工大学学报(自然科学版),1999,(04):308.
 ZhaoQilin ZhuoJiashou LiuJingchuen.The BP G S Learning Algorithms of BP Network[J].Journal of Nanjing University of Science and Technology,1999,(01):308.

备注/Memo

备注/Memo:
作者简介: 朱红 ( 1966- ), 女, 北京人, 博士生, 主要研究方向: 神经网络, E-mail:zhuhongzh@ yahoo. com. cn。
更新日期/Last Update: 2007-02-28