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
共[11]条 当前为第1条到11条
 

相关语句
神经网络
    A Multi stage Neural Network Architecture for Handwritten Chinese Character Recognition
    基于多级神经网络结构的手写体汉字识别
    Neural Network Method for Colorimetry Calibration of Video Cameras
    基于神经网络的摄像机色度标定方法(英文)
    Expert Neural Network Method for the Comprehensive Evaluation of Management Information System
    综合评价管理信息系统的专家神经网络方法
    A Novel Approach of Chinese Text Clustering Based on Self-Organizing Neural Network
    一种基于自组织神经网络的中文文本聚类新方法
    Information System (abbreviated IS) acts as a subsystem of enterprise system and enterprise's digital nerve network, its agility is an important or key factor to promote forming of organization's core competitive ability.
    信息系统作为企业系统的一个子系统,同时作为企业自身的数字神经网络,它的敏捷性是企业敏捷性的基础和构成之一,也是促进企业核心竞争力形成的关键因素。
    This paper regards the digital television market capacity as a non-linear function of the population, GDP, the average income per year of one person and the digital television charge standards, establishes the predictable model with the nerve network BP algorithm , and then carries on the forecast.
    本文首次将数字电视市场容量看作人口、国内生产总值(GDP)、人均年收入和数字电视收费标准的非线性函数,采用神经网络BP算法,对其建立预测模型并进行预测。
    In this paper, we propose a Multi stage Neural Network Architecture (MNNA) which integrates several neural networks and various feature extraction approaches into an unique pattern recognition system.
    本文提出了一种用于手写体汉字识别的多级神经网络结构(Multi-stageNeuralNetworkArchitecture,MNNA)模型。
    This paper presents a method of recognizing occluded target with fused data,which comes from three kinds of invariances such as corner, moment and high order neural network. In this paper, Dempster Shafer Evidential reasoning is selected and used for data fusion at report level. The classification experiment shows that this method effectively improves the matching precision of the recognizing system.
    论述了基于3种不变量的融合信息来识别缺损目标的方法.该方法采用Dempster-Shafer证据推理方法作为决策层的融合工具,将拐点、线矩、高阶神经网络的分类结果进行信息融合.分类实验证明,该方法可以有效地提高系统的识别精度.
    After discussing the second level low frequencies part of wavelet transform, which is rather difficult to be compressed, we can use the nonlinear mapping capacity of multi layer free forword neural network on BP algorithm. A scheme of image coding based on nonlinear predictor is put forward. Redundance among the wavelet coefficients can be ridded effectively with the help of this method.
    主要讨论了经过小波变换后较难压缩的低频子带系数特性,并据此利用基于BP算法的多层前向神经网络高度非线性映射能力,构造了一个非线性预测器,有效地去除了低频子带系数间的冗余度,在较高的保真条件下获得了较满意的压缩比
    independent color space, a multilayer feedforward network with the error backpropagation (BP) learning rule, was regarded as a nonlinear transformer realizing the mapping from the RGB color space to CIELAB color space.
    利用BP神经网络的非线性映射特性 ,实现RGB色空间到CIELAB色空间的映射 .
    The transformed color coordinates were taken as inputs of a multilayer neural network. Based on network outputs, the RGB values to be predicted were calculated.
    转换后的颜色坐标作为神经网络的输入 ,根据神经网络的输出就能得到预测的RGB值 .
 

首页上一页1下一页尾页 

 
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