bp神经网络,反向传播神经网络！感觉还不错的

以黎曼几何为理论依据，基于S.Amari的修正核函数思想提出了两种新的保角变换，用其对核函数进行数据依赖性改进，进一步提高支持向量机分类器泛化能力。以人工非线性分类问题 为对象进行研究，仿真实验结果表明采用新保角映射可以快速显著地改善分类器泛化性能，而且能大幅度地减少支持向量的数目。-Two novel conformal transformations were proposed based on the Riemannian geometry theory and S.Amari’sidea.And the kernel function was modified by the transformation in a data-dependent way.Our experimental results for theartificial nonlinear data set show that the generalization performance of support vector machines classifier is improvedremarkably and the number of support vectors is decreased greatly.

Wavelets, Approximation and Statistical Applications-Wavelets. Approximation and Statistical Applications

人工智能技术K均值算法，JAVA实现，有需要的下-K means algorithm artificial intelligence technology, JAVA realize there is a need to the next

神经网络模式识别及其实现，第10章 内含：ART 和VQ 算法。 终于上传完，本来想一次性发上来的，但结果失败了，只好一个一个发。-pattern recognition and neural network to achieve, Chapter 10 consisting of : ART algorithm and VQ. Finally upload End, originally wanted onto a one-time, but the result of the failure, but a one-fat.

采用贝叶斯正则化算法提高 BP 网络的推广能力。我们采用两种训练方法，即 L-M 优化算法（trainlm）-?捎??

BP神经网络的小应用。模拟0~1之间的三角函数曲线-BP neural network of small applications. Analog 0 to 1 between the trigonometric curve

java神经网络工具箱-neural network toolbox

介绍了神经 网络中的HOPFIELD算法的C语言实现.-Introduce a neural network algorithm HOPFIELD realize the C language.

神经网络模式识别及其实现，第九章。 内含：HOPFIELD和LAM -pattern recognition and neural network to achieve, chap. Intron : LAM and HOPFILED

AI 人工智能 在C#环境下 实现 过河问题 算法-AI