▍1. ann-and-ga-in-heat-verse-conduction
神经网络和遗传算法在热传导逆问题中应用,本文分别用BP网络、RBF网络和GA求解了一维导热反问题,分别用BP网络和GA求 解了二维导热反问题, (Neural networks and genetic algorithms in the application of the inverse problem of heat conduction)
神经网络和遗传算法在热传导逆问题中应用,本文分别用BP网络、RBF网络和GA求解了一维导热反问题,分别用BP网络和GA求 解了二维导热反问题, (Neural networks and genetic algorithms in the application of the inverse problem of heat conduction)
说明: 文中包含利用遗传算法进行优化的梯度下降神经网络的代码和教程,内容非常丰富,包含可以直接运行的代码和相关重要参考文献论文,可帮助理解,属于很综合的优秀资料,个人现分享出来供大家学习,谢谢!(This article contains the code and tutorial of gradient descent neural network optimized by genetic algorithm. The content is very rich, including the code that can be run directly and related important reference papers, which can help to understand. It is a very comprehensive and excellent material. Now I share it for you to learn. Thank you!)
说明: 用一种粒子来模拟上述的鸟类个体,每个粒子可视为N维搜索空间中的一个搜索个体,粒子的当前位置即为对应优化问题的一个候选解,粒子的飞行过程即为该个体的搜索过程.粒子的飞行速度可根据粒子历史最优位置和种群历史最优位置进行动态调整.粒子仅具有两个属性:速度和位置,速度代表移动的快慢,位置代表移动的方向。每个粒子单独搜寻的最优解叫做个体极值,粒子群中最优的个体极值作为当前全局最优解。不断迭代,更新速度和位置。最终得到满足终止条件的最优解。(Each particle can be regarded as a search individual in the n-dimensional search space, the current position of the particle is a candidate solution of the corresponding optimization problem, and the flight process of the particle is the search process of the individual. The flight speed of the particle can be dynamically adjusted according to the historical optimal position of the particle and the historical optimal position of the population There are two attributes: speed and position. Speed represents the speed of movement and position represents the direction of movement. The optimal solution searched by each particle is called individual extremum, and the optimal individual extremum in particle swarm optimization is the current global optimal solution. Iterate continuously to update the speed and position. Finally, the optimal solution satisfying the termination condition is obtained.)
加入贪婪策略和遗传算法中的变异策略的混合蚁群算法(Join the greedy strategy and mutation strategy of ant colony algorithm)
说明: 使用樽海鞘算法结合极限学习机,应用风电场数据,根据风速温度等条件对风功率进行预测,效果不错(The thalassella algorithm combined with extreme learning machine is used to predict wind power according to wind speed, temperature and other conditions with wind farm data)
风电场集电系统优化,基于遗传算法,可以直接使用(the number of wind turbines in a string for radial topology affects the wind power output)
风电场优化调度,基于改进遗传算法,内含算法及程序,2017年(wind power le=zeros(1,length(f)); le=zeros(1,length(f));)
说明: 在MATLAB使用eeglab计算脑电功率,根据频段划分,平均功率(EEG power calculation by EEG Lab)
德国奥格斯堡基于生理信号的情感识别GUI工具箱。包括心电,皮电,呼吸和肌电信号。(Augsburg, Germany-based GUI toolkit emotion recognition of physiological signals. Including ECG, galvanic skin, respiratory and EMG.)
德国奥格斯堡基于生理信号的情感识别GUI工具箱。包括心电,皮电,呼吸和肌电信号。(Augsburg, Germany-based GUI toolkit emotion recognition of physiological signals. Including ECG, galvanic skin, respiratory and EMG.)
高斯混合模型EM算法,通过EM算法来进行高斯混合模型的参数估计(Gaussian mixture model EM algorithm parameters by EM algorithm to estimate the Gaussian mixture model)
一种新的智能优化算法,水循环算法,可以用来求解优化问题(water cycle. This code is prepared for single objective function (minimization), unconstrained, and continuous problems.)
可靠性优化的遗传算法求解,粒子群算法求解,非常简单,(reliability of the genetic optimization algorithm, the PSO algorithm, is very simple.)
多移动机器人协调控制系统的研究与实现_程磊,论文论述了多机器人编队的问题,算法以及仿真环境的问题。(Multiple mobile robots Coordinated Control System Research and Implementation _ Cheng Lei, the paper discusses the problem of multi-robot formation algorithm and simulation environment.)
领航跟随法的实现,可以用于多机器人的编队控制。(The implementation of Leader-follower method, can be used in multiple robots formation control. )
pca,dpca,kpca,kspca对于故障识别、故障诊断、故障别是的应用,有很好的作用(Pca, dpca, kpca, kspca for fault recognition, faults diagnosis, especially the application of fault, have very good effect )
运用粒子群算法优化灰色预测模型的源程序,直接读取数据运行(Particle swarm optimization using gray prediction model of the source, read data directly run)
利用机器学习中神经网络(ANNbp)对UCI中鸢尾花数据集分类,150做训练样本,剩下150做测试样本。结果大概在99.6 (Using neural network machine learning (ANNbp) on the UCI iris data set classification, 150 training samples, the remaining 150 test samples. Results about 99.6 )
用遗传算法优化BP神经网络进行非线性函数拟合,程序中还编写出了单纯BP的预测函数,以及BP和GA_BP的预测误差输出程序。(using genetic algorithms optimizated BP neural network,he program has also prepared a simple BP s prediction function, as well as BP and GA_BP prediction error output of the program.)
基于核聚类的雷达信号在线分选程序,比较经典(On-line Radar Signal Sorting Procedure Based on Kernel Clustering)