泛化

一种提高BP神经网络泛化能力的改进算法

A Modified Algorithm to Improve Generalization Ability of BP Neural Network

详细阐述了防止BP网络过度训练的方法，总结了常用的增强网络泛化能力的方法。

The methods to improve the generalization ability of neural networks are summarized .

我意识到英国人如果对爱尔兰问题加以泛化的话会招惹麻烦。

I realise that an Englishman who generalises about Ireland invites trouble

基于泛化回归RBF神经网络铝带厚度控制系统的辨识

Identification Based on GR-RBF NN for Thickness Control of Aluminum Strip

IRAN算法用于非线性动态系统的在线建模，能有效地改善模型精度和泛化能力。

IRAN can improve the accuracy and generalization of model effectively for nonlinear dynamic system modeling .

所以在BP网络的误差函数中加入惩罚项是提高网络泛化能力的一个重要途径。

So adding a penalty term to the error function of BP network is an important approach to gain better generalization .

随着BP神经网络研究的逐渐深入，泛化能力作为它的一个重要评价指标也引起了人们的广泛讨论。

With the deeply research on BP neural network , generalization is aroused widely debating of people as an important evaluation index .

这种新的机器学习方法，既利用了PCA降噪的特性，又具有经典SVM泛化能力强、分类快的特性。

This new method has both the obvious de-noising ability from PCA and the generalization from SVM .

通过检测，本文所建立的BP神经网络模型具有较好的泛化能力，能够对武汉市房地产进行有效预警。

Through testing , the BP neural network model established in this paper has good generalization ability , it can make accurate judgments .

与传统的BP神经网络模型相比较，结果表明，RBF网络具有更高的精度和更好的泛化能力。

Compared with traditional BP network , the result indicated that RBF has better accuracy and adaptability of the network .

在Matlab中进行了仿真训练，并比较了两种神经网络模型的仿真效果及泛化能力。

Simulation training is carried out on Matlab , and simulation effect and generalization ability of the two neural network models are compared .

介绍了Matlab神经网络工具箱的一些重要内容，包括数据预处理、训练算法比较、网络泛化能力等。

This paper introduced some content of neural network toolbox in Matlab , including data pretreatment , training arithmetic comparison , network generalization , etc.

CMAC学习性能及泛化性能研究综述

Research on Learning and Generalization Capability of CMAC : An Overview

经检验，建立的BP神经网络有很好的泛化功能、鲁棒性好，用其检测鸡蛋大小并分级，其正确识别率为91%。

BP neural network has wonderful function and robust property , the correct discerning rate to detect egg 's grade with network is 91 % .

BP神经网络模型具有较好的泛化能力，计算精度也较高，但难以进行反馈控制计算；

The artificial neural network is of high capacity of generalization and high accuracy of calculation , but it is difficult for discharge feedback control calculation ;

神经计算中坐标变换的网络模型（CMAC）的泛化特性

Generalization of neural network model ( cmac ) for coordinate transformation in neural computation

支持向量机（supportVectorMachine，SVM）分类方法在实际二类分类问题的应用中显示出良好的学习和泛化能力，已被广泛地应用于多类分类问题的研究。

The Support Vector Machine ( SVM ) has shown excellent learning and generalization ability in the practice problems of binary classification , and has been widely employed in multi-class classification .

Modeler中的一个新功能使您可以对这些泛化流建模。

A new feature in Modeler enables you to model these generalized flows .

使用正交最小二乘法训练的RBF网络具有更小的泛化误差，更适合于实时控制应用。

The RBF network trained by OLS algorithm can get smaller generalization error , it is more suitable for real time control .

利用CMAC的局部泛化能力定量地评估设备的性能退化。

CMAC is used to assess degradation states quantitatively based on its local generalization ability .

通过对二维实数空间的数据和Iris数据进行实验，结果表明该方法聚类效果好，识别率高，且具有较好的泛化能力。

Experiment results demonstrate that the algorithm has good clustering effect and high recognition rate on R2 space data and iris data .

文章给出的是改进的神经网络的预测方法，可提高BP神经网络的收敛速度，增强网络的泛化能力，获得了很好的效果。

The authors adopt a modified forecast method of neural network , which improves convergent speed , strengthens extensive ability of BP neural network and gains a good effect .

然而，由于缺乏问题的先验知识，BP神经网络算法往往很难找到理想的网络结构，这就影响了分类器泛化能力的提高。

However , for lack of prior knowledge , it is difficult to find suitable network structure used BP neural network algorithm , which affects generalization capability of classifier .

改进RBF网络的训练算法，增强RBF网络的局部逼近能力和泛化能力，采用由模糊聚类分析获得的样本对RBF网络进行训练，在不需大量训练样本的前提下实现对短期负荷的预测。

By training RBF network using the information of selected days , short-term load forecasting without large number of samples can be realized .

人们尝试利用模拟退火、遗传算法等多种方法对BP神经网络的拓扑结构、学习方法等方面进行改进，使得它能够快速、准确的进行拟合和预测，并以此来增强BP神经网络自身的泛化能力。

People use simulated annealing , genetic algorithm and so on to improve topological structure and learning method . It can fit and forecast the neural network fast and accurately .

其次，针对经典算法BP网络存在的某些缺陷，提出了一种交替迭代算法神经网络，以提高其非线性映射能力和泛化能力。

In view of the limitations of the classic BP Neural Network , an optimal Neural Network algorithm based on alternative and iterative algorithm is put forward in this paper .

基于设计出的神经网络钻压控制器，通过MATLAB仿真测试，测试证明神经网络控制器的训练过程可进行有效的收敛，其泛化能力也达到要求。

Matlab simulation is developed with the bit pressure controller of artificial neural network , the result of simulation is positive the analyses which is convergent and high ability of expand .

原子变量类可以认为是volatile变量的泛化，它扩展了可变变量的概念，来支持原子条件的比较并设置更新。

The atomic variable classes can be thought of as a generalization of volatile variables , extending the concept of volatile variables to support atomic conditional compare-and-set updates .

具有动态记忆功能的Elman神经网络的泛化能力比较低。

The neural network of Elman has dynamic memory ability , but its extension is low .

在燃烧调整试验基础上，发展了基于神经网络的锅炉NOx排放和飞灰含碳量的响应模型，并通过试验值和模型计算值的比较，证实模型的泛化能力。

On the basis of combustion experiment , a model based on ANN for the NOx emission and unburned carbon in fly ash is developed , and the model is verified well .