icmpping

本文是2016 台湾资料科学年会前导课程“一天搞懂深度学习”的全部讲义PPT（共268页），由台湾大学电机工程学助理教授李宏毅主讲。作者在文中分四个部分对神经网络的原理、目前存在形态以及未来的发展进行了介绍。深度学习的每一个核心概念在文中都有相关案例进行呈现，通俗易懂。一天的时间搞懂深度学习？其实并不是没有可能。(This is the entire handout PPT (268 pages in total) of "a day to understand deep learning", the leading course of the 2016 Taiwan annual conference of data science. It was given by li hongyi, assistant professor of electrical engineering at Taiwan university.In this paper, the author introduces the principle, existing form and future development of neural network in four parts.Each core concept of deep learning is presented in relevant cases, which are easy to understand.)

machine learning 方面有关于Classification fundamentals的资料，语言是python(Classification fundamentals aspects of machine learning have information about language is python)

能对投影仪进行代替人的检查操作，菜单遍历以及通道切换等操作(Projector can be replaced by human inspection operations, menu traversal and channel switching operations)

实现了hadoop mapreduce模块中的wordcount例程(hadoop mapreduce wordcount)

中文篇章的关键词抽取,。。其中包括分词、去掉停用词、关键词抽取算法实现等，自己项目中实现的，欢迎下载

该文件以python为语言，通过应用机器学习中的PCA技术提取人脸特征(This document takes Python as the language and extracts facial features by applying PCA technology in machine learning)

本程序用于实现模拟退火算法计算最短路径问题,读取txt数据,最后计算出任意两点之间的距离(This program is used to realize simulated annealing algorithm to calculate the shortest path problem, read TXT data, and finally calculate the distance between any two points.)

说明：  斯坦福大学吴恩达机器学习视频课程的源代码(Source Code for Stanford University Wu Enda Machine Learning Video Course)

说明：  使用tensorflow框架搭建神经网络，从单目图像中估计深度值(Using tensorflow framework to build a neural network to estimate depth from monocular images)

使用CNN进行一维卷积，对数据进行预测估计(Using CNN to carry out one dimensional convolution to predict the data)