资源列表
CNN
- 深度学习中卷积神经网络，实现手写数字的分类，其中包含网络的初始化，训练，测试三个模块。包含mnist_uint8.mat文件，CNN入门学习程序。-Convolution depth study neural networks, digital handwritten classification, which includes the network initialization, training, testing three modules. Files contain mnist_uin
BP-algorithm
- BP算法的功能是实现一定条件下的全局最优解。-BP algorithm function is to achieve global optimal solution under certain conditions.
beibao
- 模拟退火算法是一种通用的随机搜索算法，是对局部搜索算法的扩展。与一般局部搜索算法不同，SA以一定的概率选择领域中目标值相对较小的状态，是一种理论上的全局最优算法。-Simulated annealing algorithm is a common random search algorithm is an extension of local search algorithm. Different general local search algorithm, SA with a certain
main
- 回火退火法作为模拟退火法的改进方法，当退火一定程度时讲温度升高即回火，然后在继续退火，反复即可跳出最优陷阱，保证全局最优解的求解效率质量。-Tempering annealing as an improved method of simulated annealing, speaking when the annealing temperature that is tempered to some extent, and then continue annealed repeatedly to
Stochastic-optimization-method
- 随机性多次寻优法,随机性算法能够有效地寻找全局最优解。-Stochastic optimization method many times, random algorithm can find the global optimal solution.
bp-ga-method
- 基于遗传算法的BP神经网络算法(以下简称BP—GA)就是在BP神经网络的学习过程中，将权重和阀值描述为染色体，并选取适宜的适应函数，然后进行GA迭代，直到某种意义上的收敛．-GA BP neural network algorithm (hereinafter referred to as BP-GA) is in the learning process BP neural network, the weights and thresholds described as chromosomes
shenjingwangluo
- 本代码为基于matlab的神经网络源代码，未经过训练，可用。-The code is based on a neural network matlab source code, untrained, are available.
PSO-noncon
- 粒子群算法，可以计算含非线性不等式约束和等式约束的优化问题。-PSO algorithm can be calculated with nonlinear inequality constrained optimization problems and equality constraints.
libsvm32
- matlab下libsvm工具箱，使用于32位系统-lib svm
KC_Prak_V_NN
- IN THIS PROGRAM, WE CAN USE THE NN ON VB
DE-BP
- 通过DE的方法对BP神经网络进行优化，用PM2.5数据进行验证。-On the BP neural network is optimized by using the method of DE, with PM2.5 data for validation.
ga
- 遗传算法，就是ga，就是求最优问题，自己写的一个小程序-Genetic algorithm is ga, is seeking optimization problem, write a little program