The study of the generalization ability of Multilayer Perceptrons(MLPs).
①多层感知机推广性能的定量度量。
The generalization ability of the network was improved by regularization.
为了提高网络模型的泛化能力，采用规则化调整的方法。
To enhance the generalization ability of neural networks, an improved method is studied.
从提高神经网络泛化能力的角度提出一种改进方法。
CMAC is used to assess degradation states quantitatively based on its local generalization ability.
利用CMAC的局部泛化能力定量地评估设备的性能退化。
SVM has good characteristics of simple structure, global optimum and strong generalization ability.
支持向量机分类器结构简单、可获得全局最优、泛化能力强。
The simulation indicates that the SVM has much better generalization ability than the compared methods.
算例表明相对其他方法，支持向量机有着最佳报价决策的能力。
Its main idea is to control learning machine's generalization ability by controlling its model complexity.
该理论的核心思想是通过控制学习机器的复杂度，实现对推广能力的控制。
The network possess advanced reasonable construction designs, high accuracy and strong generalization ability.
该网络结构设计先进合理，精度高，泛化能力强。
Experiment results show its better performance in the efficiency of detecting system and generalization ability.
实验表明，算法在检测系统效率和推广性方面有较好的表现。
This approach greatly improves the generalization ability of SVM classification and its application area is extended.
这一方法大大提高了支持向量机分类的泛化能力，从而大大提高了支持向量机的应用范围。
The method can learn smaller trees with lower computational complexity, but its generalization ability is not better.
用该方法生成的决策树规模小且计算复杂度低，但是泛化能力不佳。
Experiments show that this method can effectively select features while improving the generalization ability of network.
实验表明，该方法既能快速有效地删除特征，又提高了网络的泛化性能。
SVM can solve small sample problems and has good generalization ability using the principles of structural risk minimization.
支持向量机基于结构风险最小化原则，解决了小样本数据分类和泛化问题。
The support vector machine (SVM) is an algorithm based on structure risk minimizing principle and high generalization ability.
支持向量机(SVM)是一种基于结构风险最小化原理，具有很好推广性能的学习算法。
And the accuracy rate of a classification network is explained as the maximum likelihood estimation of the generalization ability.
证明了一个分类网络的测试集正确率是该网络推广能力的极大似然估计；
Kernel function is the key technology of SVM, the choice of kernel will affect the learning ability and generalization ability of SVM.
核函数是SVM的关键技术，核函数的选择将影响着支持向量机的学习能力和泛化能力。
Research results indicate that generalization ability and learning accuracy are the non decreasing function of weight adjusting ratio.
研究结果表明，在样本分布和量化级数不变时，泛化均方差和学习均方差是权调整率的非增函数。
The experimental results show that the whole target identification system has a relatively simple structure and good generalization ability.
实验结果表明，整个目标识别系统的结构简单，同时具有较好的推广能力。
SVM has been wildly used for object detection and recognition for the past decades, because of its good generalization ability and performance.
近十年来，支持向量机因其通用性和良好的性能，被广泛地用于对象检测与识别。
The fundamental issue for classification problem caring about is how to effectively improve the generalization ability of the classification system.
分类所关心的一个根本问题是如何有效地提高分类系统的泛化能力。
Support Vector machine (SVM) is a new method of machine learning. It has some advantages such as generalization ability, nonlinear and high dimensions.
支持向量机是一种新的机器学习方法，它具有推广能力强、非线性和高维数等一系列优点。
This paper proposed a selective Support Vector Machine (SVM) ensemble algorithm based on double disturbance to improve the generalization ability of SVM.
为了进一步提升支持向量机泛化性能，提出一种基于双重扰动的选择性支持向量机集成算法。
Simulation results show that LS-SVM reduces calculating complexity with high calculating speed. And it also has good generalization ability with small sample.
仿真结果表明，最小二乘支持向量机降低了计算复杂度，且有较快计算速度，在小样本情况下具有良好的泛化能力；
For increasing ensemble diversity to improve the generalization ability of learning system, three methods is given in order to create diverse neural networks.
文中还给出了三种生成差异度不同的神经元网络的方法，并通过求解实例对比了这三种方法的优化效果。
The high generalization ability of Support Vector Machine (SVM) makes it especially suitable for the classification of high-dimension data such as term-document.
支持向量机(SVM)高度的泛化能力使它特别适用于高维数据例如文档的分类。
The constringency speed and generalization ability of optimized BPNN model are better than that of simple BPNN model, and the simulation result is close to reality.
遗传算法优化的BP神经网络在收敛速度和泛化能力上都较简单的BP神经网络要好，模拟结果更接近于真实值。
Generalization ability of ANN's identification model concerns with many factors, and appropriate designed performance index function is an important influence factor.
大量研究表明，ANN模型泛化能力的改善与很多因素相关联，其中恰当的性能指标函数设计是一个重要影响因素。
Generalization ability of ANN's identification model concerns with many factors, and appropriate designed performance index function is an important influence factor.
大量研究表明，ANN模型泛化能力的改善与很多因素相关联，其中恰当的性能指标函数设计是一个重要影响因素。
应用推荐