助手标题  
全文文献 工具书 数字 学术定义 翻译助手 学术趋势 更多
查询帮助
意见反馈
   连续函数映射 的翻译结果: 查询用时:0.258秒
图标索引 在分类学科中查询
所有学科
自动化技术
更多类别查询

图标索引 历史查询
 

连续函数映射
相关语句
  continuous function map
     A STUDY ON INPUT SAMPLE REORGANIZATION FOR CONTINUOUS FUNCTION MAP NETWORKS
     连续函数映射网络样本重组的研究
短句来源
  相似匹配句对
     Extension of Continuous Mappings(I)
     连续映射的扩充I
短句来源
     ALMOST H-CONTINUOUS FUNCTIONS
     几乎H连续映射
短句来源
     The Hyperspaces of Continuous Functions
     连续函数超空间
短句来源
     Hyperspaces of Continuous Functions
     连续函数超空间
短句来源
     A STUDY ON INPUT SAMPLE REORGANIZATION FOR CONTINUOUS FUNCTION MAP NETWORKS
     连续函数映射网络样本重组的研究
短句来源
查询“连续函数映射”译词为用户自定义的双语例句

    我想查看译文中含有:的双语例句
例句
没有找到相关例句


There is such a problem in the Neural Network basic that is how to realize an arbitary continuous function by a three-layered network.In this paper,by using the Self-Organizing Feature Map competitive network presented by Kohonen in 1981,and 2M-partition definition of domain,a new method has been discussed to solve the problem of how to approximate arbitrary continuous function defined on a hypercube by utilizing a.network with definite hidden unit and a satisfactory conclusion has been obtained.The network...

There is such a problem in the Neural Network basic that is how to realize an arbitary continuous function by a three-layered network.In this paper,by using the Self-Organizing Feature Map competitive network presented by Kohonen in 1981,and 2M-partition definition of domain,a new method has been discussed to solve the problem of how to approximate arbitrary continuous function defined on a hypercube by utilizing a.network with definite hidden unit and a satisfactory conclusion has been obtained.The network architecture and learning algorithm is given in detail.

在神经网络基础理论中,有一个这样的问题:怎样用三层网络实现对任意连续函数的映射,本文利用Kohonen提出的Self-OrganizingFeatureMap竞争型网络以及区域的2M-分割概念,解决了用具有有限个隐层单元的三层网络以任意精度逼近一个连续函数的问题,具体的网络结构和学习算法已给出.

During the learning of an artificial neural network, the performance of neural network is remarkably influenced by the sequencing of the training samples. The slow converging rate and long term oblivion of the mapping network for continuous functions during learning are most frequently encountered. The influence of the sequencing of the learning samples on the network performance is investigated and the rule for the rearrangement of the order of the training samples is proposed. The ROSTA algorithm is realized...

During the learning of an artificial neural network, the performance of neural network is remarkably influenced by the sequencing of the training samples. The slow converging rate and long term oblivion of the mapping network for continuous functions during learning are most frequently encountered. The influence of the sequencing of the learning samples on the network performance is investigated and the rule for the rearrangement of the order of the training samples is proposed. The ROSTA algorithm is realized with the rule proposed and it is applied with satisfaction to the splitting of Chinese Shengmu and Yunmu of speech signals as well as to the study of the recognition of the signals of non speech service in communication networks.

研究并讨论了学习样本的排列次序对连续函数映射网络性能的影响,提出了样本次序重组的规则,据此规则实现了ROSTA算法并将其用于语音信号的声、韵母分割和通信网非话业务信号的识别研究,取得了较为理想的结果.

This paper deals with the effects of learning sample's order on continuous function map network's convergence. Sample reorganization rules are proposed to prevent information loss on network's learning process, which have been verified by theoretical analysis and computer simulation results.

本文研究了连续函数映射网络学习样本的次序对网络收敛性的影响,提出了样本次序重组的规则.数学分析和计算机仿真实验结果均表明,据此规则实现的改进型算法有效地克服了网络实时学习中存在的“记忆遗忘”现象.

 
<< 更多相关文摘    
图标索引 相关查询

 


 
CNKI小工具
在英文学术搜索中查有关连续函数映射的内容
在知识搜索中查有关连续函数映射的内容
在数字搜索中查有关连续函数映射的内容
在概念知识元中查有关连续函数映射的内容
在学术趋势中查有关连续函数映射的内容
 
 

CNKI主页设CNKI翻译助手为主页 | 收藏CNKI翻译助手 | 广告服务 | 英文学术搜索
版权图标  2008 CNKI-中国知网
京ICP证040431号 互联网出版许可证 新出网证(京)字008号
北京市公安局海淀分局 备案号:110 1081725
版权图标 2008中国知网(cnki) 中国学术期刊(光盘版)电子杂志社