资源列表
FCN.tensorflow-master
- 全卷积网络图像分割。使用python和tensorflow的实现。(Image segmentation with full convolution network.)
C51-DDQN-Keras-master
- C51-DDQN-Keras-master 分类版DDQN机器学习Demo代码(C51-DDQN-Keras-master DDQN reinfocrement learning)
19.决策树与随机森林
- 决策树和随机森林，非常实用的PPT资料，推荐(Decision tree and random forest, very useful PPT data, recommended.)
BP神经网络python简单实现
- 去掉神经元类，把功能合并入NetLayer类中，使用矩阵计算加快速度 调整代码实现批量训练方法。 优化程序中numpy库运算顺序，避免产生中间变量(Remove neuron classes, merge functions into NetLayer classes, and use matrix to calculate speed.)
Gauss Bayes
- 使用高斯贝叶斯函数对已有数据进行分类，有样本集(The Gauss Bayes function is used to classify the existing data.)
CNN
- 一种有效的特征提取算法，包含几类卷积神经网络算法代码与演示数据(An effective feature extraction algorithm includes several kinds of convolutional neural network algorithm codes and demonstration data.)
CAE
- 卷积自编码器，深度学习中的CAE，类似CNN，是深度学习的基本框架之一(Convolution self encoder, CAE in depth learning, similar to CNN, is one of the basic frameworks for deep learning.)
PCA程序
- 实现主成分分析 % Usage: % [eigvector, eigvalue] = PCA(data, options) % [eigvector, eigvalue] = PCA(data) % % Input: % data - Data matrix. Each row vector of fea is a data point. % % options.ReducedDim
遗传算法 Python
- 用Pyhon语言编写的遗传算法（ｇｅｎｅｔｉｃ ａｌｇｏｒｉｔｈｍ），包括选择交叉变异算子
PSO
- 粒子群求一元/二元函数极值，粒子群改变权值(Particle swarm optimization is used to find the extreme value of a one / two element function.)
【源代码】深度学习入门：基于Python的理论与实现
- 书籍《深度学习入门基于Python的理论与实现》源码(Book "deep learning entry based on Python theory and implementation" source code)
BP神经网络预测
- BP神经网络是目前较为简单的预测算法，但是需要要有足够的样本，本例使用神经网络算法，两步预测(BP neural network is a relatively simple prediction algorithm at present, but it needs enough samples. This example uses neural network algorithm and two-step prediction.)