1) over-generalized errors
泛化性偏误
1.
As an inevitable phenomenon in the acquisition of Chinese as a second language, the over-generalized errors can reflect the learners’ language aptitude and learning strategies better than the errors originating from the interference of the learners’ mother tongue.
与由干扰引起的偏误相比,泛化性偏误更能体现学习者的语言学能和积极的学习策略。
2) generalization error
泛化误差
1.
After the relationship among the generalization errors of the neural networks en semble, the generalization error and the diversity of the component neural netwo rk is analyzed.
该文分析了神经网络集成中成员神经网络的泛化误差、成员神经网络之间的差异度对神经网络集成泛化误差的影响,提出了一种并行学习神经网络集成方法;对参与集成的成员神经网络,给出了一种并行训练方法,不仅满足了成员网络本身的精度要求,还满足了它与其余成员网络的差异性要求;另外,给出了一种并行确定集成成员神经网络权重方法。
2.
At the same time,in order to validate its generalization performance theoretically,its generalization error upper bound is formulated and proved.
从理论上分析了该分类器的泛化性能,给出了它的泛化误差上界,并进行了实验验证。
3) Generalization error
泛化错误
4) generalization error bounds
泛化误差界
5) generalization performance
泛化性能
1.
A new algorithm for improving the generalization performance and real-time ability of feedforward neural networks;
提高前向神经网络泛化性能和实时性能的新算法
2.
Principal component analysis method to improve generalization performance of radial basis function network and its application research;
改善径向基函数网络泛化性能的主成分分析法及应用研究
3.
Support Vector Machine approach is considered a good candidate because of its good generalization performance,especially when the number of training samples is very small and the dimension of feature space is very high.
支持向量机方法被看作是对传统学习分类方法的一个好的替代,特别在小样本、高维情况下,具有较好的泛化性能。
6) generalization
[英][,dʒenrəlaɪ'zeɪʃn] [美]['dʒɛnrələ'zeʃən]
泛化性
1.
Computer simulation indicated that although fewer training samples were adopted,the recognition ratio and the generalization of this neural network was high enough.
结果表明：由减少的训练样本训练网络后，网络的样本识别率仍能达到较高水平，从而实现了减少训练样本和网络训练时间、而神经网络的识别率及泛化性不受影响的良好效
2.
It improved generalization performance of classifier.
该方法把经单独训练的具有一定差异度的单个RBF神经网络加以集成,可提高分类器的泛化性能。
补充资料：误打误撞
1.谓事先未经周密考虑。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条