资源列表
sql
- sql server的教学PPT 有利于初学者对于sql的一个大致了解 可以借鉴一下(The teaching PPT of SQL server is helpful for a beginner to learn a general understanding of SQL)
code2
- 线性神经网络和单层感知机非常相似，输入层、输出层甚至是误差迭代函数都相同，唯一的区别就是他们的传输函数不同(Linear neural network and single-layer perceptron are very similar. Input layer, output layer and even error iteration function are all the same. The only difference is their transmission function
code
- 单层感知器（Single Layer Perceptron）是最简单的神经网络。它包含输入层和输出层，而输入层和输出层是直接相连的。(The single layer perceptron is the simplest neural network. It contains the input layer and the output layer, and the input layer and the output layer are directly connected.)
code
- 人工神经网络（Artificial Neural Networks，简写为ANNs）也简称为神经网络（NNs）或称作连接模型（Connection Model），它是一种模仿动物神经网络行为特征，进行分布式并行信息处理的算法数学模型(Artificial neural network is also referred to as neural network (NNs) or connection model. It is a mathematical model for simulating
七个RBF神经网络的源程序
- 包含了RBF源代码，可以用于RBF神经网络编程，其中包括RBF聚类，K均值聚类等(It includes the RBF source code, which can be used for RBF neural network programming, including RBF clustering, K mean clustering, etc.)
MINST_DEMO
- 根据概率模型实现的QDF,LDF分类算法，有minst数据集做demo(QDF, LDF classification algorithm based on probability model, MINST data set to do demo)
bpnn
- 反向传播ANN的算法实现，里面有简单的data数据demo(Backpropagation ANN algorithm implementation, there is a simple data data demo)
GMM
- 高斯混合聚类的python实现代码，里面有data的demo(Python implementation code of Gauss mixed clustering)
create_pet_tf_record_quiz8
- 该代码将xml文件中的图片尺寸信息和物体位置信息统一进行处理，物体位置会转换成0～1之间的比例，物体名字会根据label_map转换成一个数字列表，结果会存入tfrecord中。(The code will process the image size information and object location information in the XML file uniformly, and the position of the object will be converted to
NetWorkdivide
- 神经网络分类算法 含主文件和子文件，男女生数据及说明(Main file of neural network classification algorithm)
neural network
- 自组织特征映射网络的亚洲足球水平聚类；人脸朝向识别(Asian football level clustering based on self organizing feature mapping network.Face orientation recognition)
新建压缩(zipped)文件夹
- 通过径向基函数神经网络对输入变量进行整理运算(The arrangement of input variables by radial basis function neural network)