Statistical pattern recognition algorithm package, including a linear classifica...

自适应步长BP神经网络训练算法，采用最小误差和梯度下降法更新权值- BP neural network training anaysis， realized by using error feed back, gradient descent applied updating of synaptic weights

一个反向传播算法的的原程序！值得一看，大家自己看看！-a back-propagation algorithm of the original program! An eye-catcher, we see for himself!

人工神经网络java工具箱源代码 包含BP网络，K分类和RBF网络-ANN java source code toolkit includes BP, K Classification and RBF Network

这是一个关于遗传算法的程序，包括了算法的各个过程，其实我对遗传算法也不很懂，也是刚刚开始学习阶段，希望一起进步-This is a genetic algorithm on the procedures, including all the process of the algorithm, in fact, I do not很懂of genetic algorithm, is just the beginning stages of learning, hope and progress together

新型模拟退火算法解决TSP优化问题。自能退火。可用于大多数情况下的优化问题。-New simulated annealing algorithm to solve TSP optimization problem. Zineng annealing. Can be used in most cases the optimization problem.

Adaptive Resonance Theory Brain Modeling 人工智能人工神经网络源码-Adaptive Resonance Theory Brain Modeling artificial neural network artificial intelligence source

人工神经网络BP算法 1、动态改变学习速率 2、加入动量项 3、运用了Matcom4.5的矩阵运算库（可免费下载,头文件matlib.h)， 方便矩阵运算,当然，也可自己写矩阵类 4、可暂停运算 5、可将网络以文件的形式保存、恢复-Artificial neural network BP algorithm 1, the dynamic change learning rate 2, adding momentum of 3, using the matrix calculation Matcom4.5 library (can be downloaded free of charge, the first document matlib.h), facilitate the matrix calculation, of course, can also write their own matrix Class 4, may be suspended by the operator 5, may be the form of network to the preservation, restoration

考虑3个神经元的hopfield网络，每个神经元有一个阀值和一个权重，定义存储在网络中的目标平衡点中为矩阵T的两个三指定存储在网络中的目标平衡点 -Consider three neurons hopfield network, each neuron has a threshold and a weight, the definition is stored in the network, the goal of equilibrium point for the matrix T of the two three-designated storage in the network

遗传算法和神经网络的结合应用，通过Visual C++环境来实现该功能，使计算能力更强-Genetic algorithms and neural networks combination of applications, through the Visual C++ environment to achieve this feature, so that more computing power