查询词典 neural network

According to the ensemble neural network model established in this paper, the estimation result showed that the network had good stability and prediction accuracy and the estimation absolute mean relative error of 207 samples was 8.62%.

估算结果表明，所建立的神经网络集成模型，其网络有良好的稳定性和预测精度，207个样本估算的绝对平均相对误差为8.62%。

By making up of time-frequency local property and multi-scale analytical capability of wavelet transformation and self-learning and prediction function of artificial neural network,chapter three develops a prediction model loose combining wavelet analysis and Radial Basis Functionsneural network,abbreviated as Wavelet-RBFNN.

第三章利用小波变换的时频局域化特性和多尺度分析能力及神经网络的自学习、预测功能，通过小波分析与神经网络的松散型结合方式，建立小波分析和径向基函数神经网络(Wavelet-RBFNN)预测模型。

Aimed at the dynamic characteristics of disparity gradient neural network, it is concluded that the network is globally asymptotically stable.

着重考察视差梯度神经网络的动态性质，用能量函数的方法分析网络的稳定性，得出网络是渐近稳定的结论，并通过实验得到验证。

In light of the technical flow of coal gasification and demand of Texaco gasifier temperature soft measurement, many questions about modeling, such as selections of auxiliary variable, collection and disposal of fields data, are discussed. And the modeling of gasifier soft measurement is composed by two methods, which are fuzzy neural network and radial basic function network.

以焦化厂德士古煤气化炉为对象，根据煤气化流程的工艺分析，针对德士古气化炉膛温度软测量的需要，研究了辅助变量选择，数据采集与处理，以及利用模糊神经网络和RBF网络建立炉温软测量模型等问题，建立了炉温软测量系统。

The system consists of two main parts. One is status recognition system of calcine band flame, which is composed of image capturing, preprocessing, segmentation, feature extraction and pattern recognition. The other is neural network control system using Gaussian potential function network.

系统主要由两部分组成，一部分是回转窑煅烧带火焰燃烧状态识别系统，包括火焰图象获取、预处理、分割、特征提取与识别；另一部分是基于高斯基函数神经网络的控制系统。

Neural Network Recognition of simple figures...Feature extraction procedure to obtain characteristic matrix, as the network input.

详细说明：神经网络识别简单的数字，程序通过特征提取获得特征矩阵，作为网络输入。

Sending the composed characteristic vector into probabilistic neural network the network training and disturbance classification are realized.

将提取的特征矢量送入概率神经网络实现网络训练和扰动分类。

Since the character of network capability can also be influenced by the processing function of hidden neurons, a Chebyshev orthogonal neural network, in which the Chebyshev function is chosen for the hidden unit processing function, is proposed and the optimization algorithm under norm‖x‖〓 is investigated.

由于网络隐层神经元处理函数对网络性能也有重要影响，故将Chebyshev函数选为隐单元的处理函数而提出Chebyshev正交神经网络，并讨论了一致范数‖x‖〓意义下的优化算法。

A neural network approach for the constrained via minimization in multi-layer VLSI/PCB routing based on Hopfield network is proposed.

本文提出了一个基于Hopfield网络的VLSI/PCB多层布线中的有约束通孔最小化方法。

Based on neural network identification procedures, procedures adopted a three-tier network training BP, with its defi...

基于神经网络的识别程序，程序采用三层BP网络训练，采用了普通定义中加入动量因子的训练法，精确度很高。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。