人工神经网络matlab编程，BP网络实例 入境旅游人数的预测结果对于旅游管理部门和政府部门有着重要的参考意义,寻求科学合理的预测模型是保障预测结果准确可靠的关键。根据我国入境旅游人数的实际情况,建立由一个输入层、一个隐含层、一个输出层构成的三层BP 网络模型-ANN Matlab programming, BP examples tourist arrivals in the forecast results for the tourism management and government sectors have important reference value, search for a scientific and rational prediction model is to ensure accurate and reliable prediction of the key. According to China"s tourist arrivals in the actual situation, and establish an input layer, a hidden layer, an output layer consisting of a three-tier network model BP

HTK系列的，0.98参考资料，应该挺有用的，大家自己看看吧！-HTK Series, 0.98 Reference should be quite useless, we all see!

Principles of Data Mining是数据挖掘领域里面又一本经典的教材，呵呵，希望对大家有帮助-Principles of Data Mining is a data mining inside another in this classic textbook, Oh, you want to help

神经网络C程序的第10章-neural network C procedures for the Chapter 10

这是我自己做的改进的遗传算法，主要是克服遗传算法的早熟问题-This is what I want done to improve the genetic algorithm, which is aimed at overcoming the genetic algorithm early problems

基于VC开发的遗传算法源程序，有详尽的注释说明-based on the development of the VC genetic algorithm source files, a detailed Explanatory notes

BLDC建模及神经网络控制，建模讲述的很详细，难得的论文。-BLDC modeling and neural network control, modeling, described in great detail, rare papers.

一个简单灵活的数据挖掘实验平台，算法基本为空，但提供读数据，基本数据预处理功能，欢迎大家使用，共同提高。-a simple and flexible experimental data mining platform, the basic algorithm for air, but for reading data, the basic data preprocessing functions Everyone is welcome to use together.

针对目前粒子群算法（Particle Swarm Optimization）一般是用MATLAB实现的，对PSO算法用C实现的代码-In view of the current PSO (Particle Swarm Optimization) is generally used MATLAB" s implementation of the PSO algorithm implementation using C code

仿真1：首先把网络温度参数T固定在100，按工作规则共进行1000次状态更新,把这1000次状态转移中网络中的各个状态出现的次数Si（i＝1，2，…，16）记录下来 按下式计算各个状态出现的实际频率： Pi=Si/∑i=1,NSi=Si/M 同时按照Bo1tzmann分布计算网络各个状态出现概率的理论值： Q（Ei）=（1/Z）exp（-Ei/T） 仿真2：实施降温方案，重新计算 采用快速降温方案：T（t）= T0/（1+t） T从1000降到0.01，按工作规则更新网络状态 当T=0.01时结束降温，再让T保持在0.01进行1000次状态转移，比较两种概率-a simulation : First of all network parameters temperature T fixed at 100 and, according to the rules for a total of 1000 to update the state, this state of the 1000 network transfer of all states for the number of Si (i = 1, 2, ..., 16) all recorded determined by the formula state-of the actual frequency : Pi = Si/i = 1, NSi = Si/M in accordance with Bo1tzmann distributed computing network of states all probability the theoretical value : Q (Ei) = (1/Z) exp (- Ei/T) Simulation 2 : implementation of cooling, re-using rapid cooling programs : T (t) = T0/(1 t) T dropped to 0.01 from 1000 and, according to the rules updated network state when T = 0.01 at the end of cooling, let T at 0.01 for the 1000 state tran