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
   training algorithm 的翻译结果: 查询用时:0.009秒
图标索引 在分类学科中查询
所有学科
自动化技术
计算机软件及计算机应用
数学
物理学
无线电电子学
电信技术
植物保护
林业
更多类别查询

图标索引 历史查询
 

training algorithm     
相关语句
  训练算法
     TFIDF_-NB Co-Operative Training Algorithm
     TFIDF_-NB协同训练算法
短句来源
     This thesis studies the incremental training algorithm of support vector machine (SVM) and its application in process control.
     本论文主要研究了支持向量机(Support Vector Machine,简称SVM)增量型训练算法及其在控制领域中的应用。
短句来源
     L-M Training Algorithm for Load Forecast Model of BP Artificial Neural Network
     BP人工神经网络负荷预测模型的L-M训练算法
短句来源
     Levenberg-Marquardt algorithm is a fast training algorithm for neural network.
     Levenberg-Marquardt算法是BP神经网络的一种改进训练算法,可以实现神经网络的快速训练。
短句来源
     And then,the structure design and training algorithm of RBF neural network theory are discussed,emphsized in the calling function and the calculation steps of RBF center and width.
     然后,从径向基函数(RBF)神经网络结构、网络设计和网络训练算法等方面论述了RBF神经网络理论,着重说明RBF网络的调用及径向基函数中心和宽度的确定步骤.
短句来源
更多       
  学习算法
     Experimental results for speaker identification indicate that the system and its MCE training algorithm attain 98.9% identification accuracy using 5 second clean speech utterances and 86.2% accuracy using 15 second telephone speech utterances with a 20 speaker population.
     实验结果表明, 该系统及其MCE学习算法在20个说话人辨认应用中利用5s清晰语音获得98.9%的辨认率,利用15s电话语音获得86.2%的辨认率。
短句来源
     MLSVM4—An SVM Fast Training Algorithm Based on Multi-Lagrange Multiplier
     MLSVM4——一种多乘子协同优化的SVM快速学习算法
短句来源
     Fast Training Algorithm of BP Wavelet Neural Network
     BP小波神经网络快速学习算法研究
短句来源
     2. A fast SVM training algorithm based on boundary samples selection is proposed (BSS-SVM).
     ● 根据SVM的分类判决面仅由支持向量决定的特点,提出了基于边界样本选择的快速SVM学习算法(BSS-SVM)。
短句来源
     Using Genetic Algorithm to Improve BP Training Algorithm
     利用遗传算法改进BP学习算法
短句来源
更多       
  训练规则
     This paper proposes a novel high-order CMAC_type neural network via the Newton's forward interpolation (NFI-CMAC), which is capable of implementing error-free approximations to multi-variable polynomial functions of arbitrary order, including interpolation algorithm and training algorithm.
     基于牛顿前向插值公式提出一种对多维函数可实现任意阶逼近的新型CMAC神经网络———NFI CMAC,详细讨论了其插值算法、训练规则及寻址机制.
短句来源
  训练算法的
     Improvement in the Training Algorithm of BP Neural Networks
     BP神经网络训练算法的改进
短句来源
     Development of a Training Algorithm for GAL Neural Network
     GAL神经网络训练算法的改进
短句来源
     An Improvement on Training Algorithm of Profile Hidden Markov Model
     剖面隐马氏模型训练算法的改进
短句来源
     A radial basis function neural network based estimation algorithm of multi targets direction of arrival in fuze smart antenna system is put forward, and design of architecture and network training algorithm for such fuze smart antenna are given in this article.
     提出了一种基于径向基函数 ( RBF)神经网络的引信智能天线多目标方向估计算法 ,对引信智能天线进行了结构和训练算法的设计。
短句来源
     (4) The paper has studied the structure and training algorithm of self-recursion neural network.
     (4)研究了自递归神经网络的结构及训练算法,利用LyaPunov方法研究了自递归神经网络训练算法的收敛性和稳定性,并首次利用自递归神经网络来反演轨道交通引起地面振动的振动场。
短句来源
更多       

 

查询“training algorithm”译词为其他词的双语例句

 

查询“training algorithm”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
为了更好的帮助您理解掌握查询词或其译词在地道英语中的实际用法,我们为您准备了出自英文原文的大量英语例句,供您参考。
  training algorithm
In this paper we use Minimum Classification Error (MCE) training algorithm for feature dimensionality reduction and classification on Daterding and GLASS databases.
      
A Modified Minimum Classification Error (MCE) Training Algorithm for Dimensionality Reduction
      
It implements the popular backpropagation training algorithm as three distinct time-exclusive FPGA configurations: feed-forward, backpropagation and update.
      
The process of mapping a neural network to a sub-threshold architecture requires the proper selection of a training algorithm.
      
With the new parallel training algorithm, thousands of amino acids can be processed in reasonable amount of time.
      
更多          


In this paper the iterative training techniques are successfully applied to the diagnosis of the degree of heart mitral stenosis, which has achieved an accuracy of 93% in clinical work.As to the unlinear seperable training pattern sets, the concept of minimum isolation is proposed and two algorithms in [4], [5], [6] are improved.As for the best projection of multi-category training pattern sots to the one dimension space in favour of seperability, the concepts of coaxial linear seperability...

In this paper the iterative training techniques are successfully applied to the diagnosis of the degree of heart mitral stenosis, which has achieved an accuracy of 93% in clinical work.As to the unlinear seperable training pattern sets, the concept of minimum isolation is proposed and two algorithms in [4], [5], [6] are improved.As for the best projection of multi-category training pattern sots to the one dimension space in favour of seperability, the concepts of coaxial linear seperability and coaxial monotonous configuration of multi-category training pattern sets are introduced and three iterative training algorithms are proposed to solve this problem.

在本文中,我们结合医疗诊断的实际情况,成功地把训练迭代技术应用于线性判别函数的建立,使计算机在心脏二尖瓣狭窄口径的临床诊断中准确率达到93%.对于非线性可分训练模式集,本文引入了最小隔离的概念,并改进了文献[4]、[5]、[6]所提出的二个启发式算法,大大提高了计算速度,节省了存贮空间.对于多范畴训练模式集在一维空间上的最佳投影问题,本文提出了多范畴训练模式集的同轴线性可分及同轴单调格局的概念,推导并证明了三个训练迭代算法,为求取最佳投影方向开辟了一条新的途径.

A speaker-dependent isolated word real-time recognition interface to a microcomputer is described in this paper. Various feasible algorithms are compared with each other according to the features of the Chinese speech and the requirements of the microcomputer for recognizing isolated word in realtime. Some new simple and efficient algorithias are proposed: a two-pass end-point detecting algorithm, a multi-stage tree decision algorithm, and the hybrid training and trace training algorithm. They notably...

A speaker-dependent isolated word real-time recognition interface to a microcomputer is described in this paper. Various feasible algorithms are compared with each other according to the features of the Chinese speech and the requirements of the microcomputer for recognizing isolated word in realtime. Some new simple and efficient algorithias are proposed: a two-pass end-point detecting algorithm, a multi-stage tree decision algorithm, and the hybrid training and trace training algorithm. They notably save the calculation time and improve the recognition accuracy.The proposed recognition interface is simple in structure and responsive to real-time. It has achieved a 95% recognition rate in average under different testing conditions.

本文介绍一种专人、孤立词的微机语音识别接口,提出的两级端点判定算法、多级树状判识算法,以及混合训练和跟踪训练算法,简单有效,显著减少了计算时间和改善了识别性能。根据上述原理制成的微机语音识别接口,结构简单,响应实时,在各种试验条件下平均识别率为95%,该接口已通过鉴定并移交生产和使用。

This paper introduces the basic structure and main concepts in multilayerneural neural network, and the principle of the back--propagation learingalgorithm is formulated and according to the derivation the procedure inthe back-propagation training algorithm is discribed .Finally,the new methodto estimate angles of arrival from plane waves impinging on array of sensorsis presented. The simulatiion results in variable sample times are consistentwith expectation.

本文介绍了多层神经网络的基本结构和主要概念,并对训练多层神经网络的Back-Propagation学习算法(即后向传递误差算法,简称后向算法)的原理和实施步骤作了详尽的分析和推导。在多层神经网络中运用这一算法,提出了平面波方位角估测的新方法。计算机模拟结果显示,这一方法是可行的。

 
<< 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training algorithm的内容
在知识搜索中查有关training algorithm的内容
在数字搜索中查有关training algorithm的内容
在概念知识元中查有关training algorithm的内容
在学术趋势中查有关training algorithm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