采用贝叶斯正则化算法提高BP网络的推广能力。在本例中，将采用两种训练方法，即L-M优化算法（trainlm)和贝叶斯正则化算法（trainbr),用以训练BP网络，使其能够拟合某一附加有白噪声的正弦样本数据。-The use of Bayesian regularization algorithm for BP network to improve generalization ability. In this case, two types of training methods will b

使用LMS算法实现的自适应滤波器范例，对一个加白噪声的正弦信号滤波。并且比较不同步长的滤波器的迭代次数。-LMS algorithm using adaptive filter example, a sinusoidal signal plus white noise filter. And less synchronized long filter iterations.

matlab例程，主要实现神经网络的辨识（不是应用工具箱），其中包含多个子文件，包含高斯白噪声的生成，bp神经网络，hopfield神经网络等的辨识。,matlab routine identification of neural network (not application toolbox), which contains multiple subfolders containing white Gaussian noise generated bp neural network, hop

在demo中，用EKF和有噪声的EKF训练非线性、非平稳数据。-In this demo, I use the EKF and EKF with noise adaptation to train a neural network with data generated a nonlinear, non-stationary state space model. Adaptation is done by matching the innovations ensemble covariance