资源列表
基于SOM的数据分类
- SOM神经网络也属于自组织型学习网络，只不过更特殊一点它属于自组织特征的映射网络。该网络是由一个全连接的神经元阵列组成的无教师，自组织，自学习的网络。(SOM neural network also belongs to self-organizing learning network, but more specifically, it belongs to self-organizing feature mapping network. The network is a non-teache
pytorch-a2c-ppo-acktr-master
- 改代码为ACKTR代码，该算法比传统的TRPO和DQN在运行速度和计算量都有很大的提升(scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation)
tensorflow
- tensorflow的简单应用与入门学习，快速上手tensorflow(Tensorflow's simple application and entry learning, quick start tensorflow)
.rar
- 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));)
MATLAB
- 马尔科夫模型，包括终极预测概率，非常好用，通俗易懂(The Markoff model, including the ultimate prediction probability, is very easy to use and easy to understand.)
python machine learning
- 作者是Sebastian Raschka，密歇根州立大学的博士生，他在计算生物学领域提出了几种新的计算方法，还被科技博客Analytics Vidhya评为GitHub上最具影响力的数据科学家。他有一整年都使用Python进行编程的经验，同时还多次参加数据科学应用与机器学习领域的研讨会。在数据科学、机器学习以及Python等领域他拥有丰富的演讲和写作经验，本书可使得不具备机器学习背景的人设计出由数据驱动的解决方案。(The author, Sebastian Raschka, a PhD stu
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.)
MATLABcode
- 采用bp对男女生样本数据中的身高，体重，喜欢数学，喜欢文学，喜欢运动，设计男女生分类器，并计算模型预测性能（包含SE,SP,ACC和AUC ）。(Using bp for height and weight in male and female sample data, like math, like literature, like sports, design boys and girls classifiers, and calculate model prediction perform
GAOT
- 基于改进的遗传算法，简单易懂。适合初学者使用，是分布式电源的选址定容的算法(Classical genetic algorithm is simple and easy to understand. It is suitable for beginners to use. It is an algorithm for locating and sizing distributed power.)
TrAdaboost
- 迁移学习中经典算法Tradaboost的python实现(Python implementation of classical algorithm Tradaboost in transfer learning)
05 竞争神经网络与SOM神经网络
- 里面有两个神经网络原理的PPT,竞争神经网络和SOM神经网络，还有一个实际案例————矿井突水水源的判别。(There is a neural network principle of PPT, competitive neural network and SOM neural network, there is also a practical case - the identification of mine water inrush.)