资源列表
DTLZ_PF_Generator
- DTLZ测试函数生成真实Pareto前端(DTLZ test function to generate true Pareto front)
fuheyuce
- 基于BP神经网络的电力系统日负荷预测，模型采用24个输入，24个输出，训练次数为10000，训练目标为0.5，学习速率设置为0.1。(Load forecasting based on BP neural network, the model uses 24 inputs, 24 outputs, the number of training is 10000, the training target is 0.5, the learning rate is set to 0.1.)
Genetic_Algotithm
- 用遗传算法求y=x*sin(10*pi*x)+2的最大值 -1=<x<=2 精确到6位小数 pow(2,21)<3*1000000<pow(2,22) 编码的二进制长度为22 (Using genetic algorithms seek y = x* sin (10* pi* x)+2 maximum-1 = <x<=2)
模糊神经网络 边坡
- 一类模糊神经网络用于边坡分类预测，注释详细，内容丰富(A kind of fuzzy neural network is used for slope classification prediction, with detailed annotations and rich content.)
confusion_matrix1
- 只有一个文件，调用函数即可生成混淆矩阵，参数可在文件中更改(Call the function to generate a confusion matrix, parameters can be changed in the file)
tbtained-numerical
- 用数值方法来求解雅克比矩阵的迭代过程,并且有仿真结果(The iterative process of Jacobian matrix is solved by numerical method, and the simulation results are obtained.)
tick
- 采用卡尔曼滤波的方法对两只股票走势相近的股票进行预测，进行低买高卖的操作，从中获利。(Kalman filter method is used to predict two stocks with similar trend, and the operation of buying low and selling high is carried out to profit from it.)
python_work
- 用tensorflow设计以三层的神经网络进行曲线拟合，采用梯度下降法。(Tensorflow is used to design three layers of neural network for curve fitting and gradient descent method.)
DNN
- 利用python3完整实现DNN，包括前向传播和反向传播。实现一个2次函数的拟合。(Complete implementation of DNN using python3, including forward propagation and reverse propagation. Implement a quadratic function fitting.)
MATLAB
- matlab使用layrecnet实现循环神经网络rnn(Matlab uses recurrent neural network to implement recurrent neural network RNN.)
entropy
- 求解信号的香农熵和指数熵，分别从功率谱和奇异谱的角度求解(The Shannon entropy and exponential entropy of signals are obtained.)
DBN
- 深度信念网络，神经网络的一种。既可以用于非监督学习，类似于一个自编码机；也可以用于监督学习，作为分类器来使用。(Deep belief network, a kind of neural network. It can be used for unsupervised learning, similar to a self-coding machine, or supervised learning, as a classifier.)