|
| 1 | +# 机器学习资源 Machine learning |
| 2 | + |
| 3 | + |
| 4 | + |
| 5 | +**致力于分享最新最全面的机器学习资料,欢迎你成为贡献者!** |
| 6 | + |
| 7 | + |
| 8 | + |
| 9 | +**[Machine learning surveys](https://github.com/metrofun/machine-learning-surveys/)** |
| 10 | + |
| 11 | + |
| 12 | + |
| 13 | +**[快速入门TensorFlow](https://github.com/aymericdamien/TensorFlow-Examples)** |
| 14 | + |
| 15 | + |
| 16 | + |
| 17 | +- - - |
| 18 | + |
| 19 | + |
| 20 | + |
| 21 | +## 预备知识 Prerequisite |
| 22 | + |
| 23 | + |
| 24 | + |
| 25 | +- Python |
| 26 | + |
| 27 | + - [Learn X in Y minutes](https://learnxinyminutes.com/docs/python/) |
| 28 | + |
| 29 | + - [Python机器学习互动教程](https://www.springboard.com/learning-paths/machine-learning-python/) |
| 30 | + |
| 31 | + |
| 32 | + |
| 33 | +- Markdown |
| 34 | + |
| 35 | + - [Mastering Markdown](https://guides.github.com/features/mastering-markdown/) - Markdown is a easy-to-use writing tool on the GitHu. |
| 36 | + |
| 37 | + |
| 38 | + |
| 39 | +- R |
| 40 | + |
| 41 | + - [R Tutorial](http://www.cyclismo.org/tutorial/R/) |
| 42 | + |
| 43 | + |
| 44 | + |
| 45 | +- Python和Matlab的一些cheat sheet:http://ddl.escience.cn/f/IDkq 包含: |
| 46 | + |
| 47 | + - Numpy、Scipy、Pandas科学计算库 |
| 48 | + |
| 49 | + - Scikit-learn机器学习库、Keras深度学习库 |
| 50 | + |
| 51 | + - Matlab科学计算 |
| 52 | + |
| 53 | + - Matplotlib画图 |
| 54 | + |
| 55 | + |
| 56 | + |
| 57 | +- - - |
| 58 | + |
| 59 | + |
| 60 | + |
| 61 | + |
| 62 | + |
| 63 | +## 理论 Theory |
| 64 | + |
| 65 | + |
| 66 | + |
| 67 | +- ### 深度学习 Deep learning |
| 68 | + |
| 69 | + |
| 70 | + |
| 71 | +- ### [强化学习 Reinforcement learning](https://github.com/allmachinelearning/ReinforcementLearning) |
| 72 | + |
| 73 | + |
| 74 | + |
| 75 | +- ### [迁移学习 Transfer learning](https://jindongwang.github.io/transferlearning/) |
| 76 | + |
| 77 | + |
| 78 | + |
| 79 | +- ### [分布式学习系统 Distributed learning system](https://github.com/allmachinelearning/Deep-Learning-System-Design) |
| 80 | + |
| 81 | + |
| 82 | + |
| 83 | + |
| 84 | + |
| 85 | +- - - |
| 86 | + |
| 87 | + |
| 88 | + |
| 89 | + |
| 90 | + |
| 91 | +## 应用 Applications |
| 92 | + |
| 93 | + |
| 94 | + |
| 95 | +- ### 计算机视觉/机器视觉 Computer vision / machine vision |
| 96 | + |
| 97 | + |
| 98 | + |
| 99 | +- ### [自然语言处理 Natural language procesing](https://github.com/Nativeatom/NaturalLanguageProcessing) |
| 100 | + |
| 101 | + |
| 102 | + |
| 103 | +- ### 语音识别 Speech recognition |
| 104 | + |
| 105 | + |
| 106 | + |
| 107 | +- ### 生物信息学 Bioinfomatics |
| 108 | + |
| 109 | + |
| 110 | + |
| 111 | +- ### 医疗 Medical |
| 112 | + |
| 113 | + |
| 114 | + |
| 115 | +- ### [行为识别 Activity recognition](https://github.com/jindongwang/activityrecognition) |
| 116 | + |
| 117 | + |
| 118 | + |
| 119 | +- ### [人工智能(多智能体) Artificial Intelligence(Multi-Agent)](http://ddl.escience.cn/f/ILKI) |
| 120 | + |
| 121 | + |
| 122 | + |
| 123 | + |
| 124 | + |
| 125 | +- - - |
| 126 | + |
| 127 | + |
| 128 | + |
| 129 | +## 文档 notes |
| 130 | + |
| 131 | + |
| 132 | + |
| 133 | +- [综述文章汇总](https://github.com/allmachinelearning/MachineLearning/blob/master/notes/survey_readme.md) |
| 134 | + |
| 135 | + |
| 136 | + |
| 137 | +- [近200篇机器学习资料汇总!](https://zhuanlan.zhihu.com/p/26136757) |
| 138 | + |
| 139 | + |
| 140 | + |
| 141 | +- [机器学习入门资料](https://github.com/allmachinelearning/MachineLearning/blob/master/notes/MLMaterials.md) |
| 142 | + |
| 143 | + |
| 144 | + |
| 145 | +- [MIT.Introduction to Machine Learning](http://ddl.escience.cn/f/Iwtu) |
| 146 | + |
| 147 | + |
| 148 | + |
| 149 | +- [东京大学同学做的人机交互报告](https://github.com/allmachinelearning/MachineLearning/blob/master/notes/FieldResearchinChina927-104.pdf) |
| 150 | + |
| 151 | + |
| 152 | + |
| 153 | +- [人机交互简介](https://github.com/jindongwang/HCI) |
| 154 | + |
| 155 | + |
| 156 | + |
| 157 | +- [人机交互与创业论坛](https://github.com/allmachinelearning/MachineLearning/blob/master/notes/%E4%BA%BA%E6%9C%BA%E4%BA%A4%E4%BA%92%E4%B8%8E%E5%88%9B%E4%B8%9A%E8%AE%BA%E5%9D%9B.md) |
| 158 | + |
| 159 | + |
| 160 | + |
| 161 | +- [职场机器学习入门](https://github.com/allmachinelearning/MachineLearning/blob/master/notes/%E8%81%8C%E5%9C%BA-%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E5%85%A5%E9%97%A8.md) |
| 162 | + |
| 163 | + |
| 164 | + |
| 165 | +- [机器学习的发展历程及启示](http://mt.sohu.com/20170326/n484898474.shtml), (@Prof. Zhihua Zhang/@张志华教授) |
| 166 | + |
| 167 | + |
| 168 | + |
| 169 | +- [常用的距离和相似度度量](https://github.com/allmachinelearning/MachineLearning/blob/master/notes/distance%20and%20similarity.md) |
| 170 | + |
| 171 | + |
| 172 | + |
| 173 | +- - - |
| 174 | + |
| 175 | + |
| 176 | + |
| 177 | +## 课程与讲座 Course and talk |
| 178 | + |
| 179 | + |
| 180 | + |
| 181 | +- [斯坦福机器学习入门课程](https://www.coursera.org/learn/machine-learning),讲师为Andrew Ng,适合数学基础一般的人,适合入门,但是学完会发现只是懂个大概,也就相当于什么都不懂。省略了很多机器学习的细节 |
| 182 | + |
| 183 | +- [Stanford CS 229](http://cs229.stanford.edu/materials.html), Andrew Ng机器学习课无阉割版,Notes比较详细 |
| 184 | + |
| 185 | +- [CMU 10-702 Statistical Machine Learning](http://www.stat.cmu.edu/~larry/=sml/), 讲师是Larry Wasserman,应该是统计系开的机器学习,非常数学化,第一节课就提到了RKHS(Reproducing Kernel Hilbert Space),建议数学出身的同学看或者是学过实变函数泛函分析的人看一看 |
| 186 | + |
| 187 | +- [CMU 10-715 Advanced Introduction to Machine Learning](https://www.cs.cmu.edu/~epxing/Class/10715/),同样是CMU phd级别的课,节奏快难度高 |
| 188 | + |
| 189 | +- Coursera上国立台湾大学[林轩田](https://www.coursera.org/instructor/htlin)开的两门课:[机器学习基石](https://www.coursera.org/course/ntumlone)(适合入门),[机器学习技法](https://www.coursera.org/course/ntumltwo)(适合提高)。 |
| 190 | + |
| 191 | +- [Machine Learning for Data Analysis](https://www.coursera.org/learn/machine-learning-data-analysis), Coursera上Wesleyan大学的Data Analysis and Interpretation专项课程第四课。 |
| 192 | + |
| 193 | +- [Neural Networks for Machine Learning](https://www.coursera.org/learn/neural-networks), Coursera上的著名课程,由Geoffrey Hinton教授主讲。 |
| 194 | + |
| 195 | +- 斯坦福大学Feifei Li教授的[CS231n系列深度学习课程](http://cs231n.stanford.edu/)。Feifei Li目前是Google的科学家,深度学习与图像识别方面的大牛。这门课的笔记可以看[这里](https://zhuanlan.zhihu.com/p/21930884)。 |
| 196 | + |
| 197 | +- Max Planck Institute for Intelligent Systems Tübingen[德国马普所智能系统研究所2013的机器学习暑期学校视频](https://www.youtube.com/playlist?list=PLqJm7Rc5-EXFv6RXaPZzzlzo93Hl0v91E),仔细翻这个频道还可以找到2015的暑期学校视频 |
| 198 | + |
| 199 | +- 知乎Live:[我们一起开始机器学习吧](https://www.zhihu.com/lives/792423196996546560),[机器学习入门之特征工程](https://www.zhihu.com/lives/819543866939174912) |
| 200 | + |
| 201 | + |
| 202 | + |
| 203 | +- - - |
| 204 | + |
| 205 | + |
| 206 | + |
| 207 | + |
| 208 | + |
| 209 | + |
| 210 | + |
| 211 | + |
| 212 | + |
| 213 | + |
| 214 | + |
| 215 | +## 相关书籍 reference book |
| 216 | + |
| 217 | + |
| 218 | + |
| 219 | + |
| 220 | + |
| 221 | + |
| 222 | + |
| 223 | +- 入门读物 [The Elements of Statistical Learning(英文第二版),The Elements of Statistical Learning.pdf](http://ddl.escience.cn/ff/emZH) |
| 224 | + |
| 225 | + |
| 226 | + |
| 227 | +- [机器学习](https://book.douban.com/subject/26708119/), (@Prof. Zhihua Zhou/周志华教授) |
| 228 | + |
| 229 | + |
| 230 | + |
| 231 | +- [统计学习方法](https://book.douban.com/subject/10590856/), (@Dr. Hang Li/李航博士) |
| 232 | + |
| 233 | + |
| 234 | + |
| 235 | +- [一些Kindle读物](http://ddl.escience.cn/f/IwWE): |
| 236 | + |
| 237 | + |
| 238 | + |
| 239 | + - 利用Python进行数据分析.azw3 |
| 240 | + |
| 241 | + - 跟老齐学Python:从入门到精通.azw3 |
| 242 | + |
| 243 | + - Python与数据挖掘 (大数据技术丛书) - 张良均.azw3 |
| 244 | + |
| 245 | + - Python学习手册.azw3 |
| 246 | + |
| 247 | + - Python性能分析与优化.mobi |
| 248 | + |
| 249 | + - Python数据挖掘入门与实践_7242.azw3 |
| 250 | + |
| 251 | + - Python数据分析与挖掘实战(大数据技术丛书) - 张良均.azw3 |
| 252 | + |
| 253 | + - Python科学计算(第2版).azw3 |
| 254 | + |
| 255 | + - Python计算机视觉编程 [美] Jan Erik Solem.azw3 |
| 256 | + |
| 257 | + - python核心编程(第三版).azw3 |
| 258 | + |
| 259 | + - Python核心编程(第二版).azw3 |
| 260 | + |
| 261 | + - Python高手之路 - [法] 朱利安·丹乔(Julien Danjou).azw3 |
| 262 | + |
| 263 | + - Python编程快速上手 让繁琐工作自动化.azw3 |
| 264 | + |
| 265 | + - Python编程:从入门到实践.azw3 |
| 266 | + |
| 267 | + - Python3 CookBook中文版.mobi |
| 268 | + |
| 269 | + - 终极算法机器学习和人工智能如何重塑世界 - [美 ]佩德罗·多明戈斯.azw3.azw3 |
| 270 | + |
| 271 | + - 机器学习系统设计 (图灵程序设计丛书) - [美]Willi Richert & Luis Pedro Coelho.azw3.azw3 |
| 272 | + |
| 273 | + - 机器学习实践指南:案例应用解析(第2版) (大数据技术丛书) - 麦好.azw3 |
| 274 | + |
| 275 | + - 机器学习实践 测试驱动的开发方法 (图灵程序设计丛书) - [美] 柯克(Matthew Kirk).a.azw3 |
| 276 | + |
| 277 | + - 机器学习:实用案例解析 (O'Reilly精品图书系 |
| 278 | + |
| 279 | + |
| 280 | + |
| 281 | +- [Packt每日限免电子书精选](http://ddl.escience.cn/f/IS4a): |
| 282 | + |
| 283 | + |
| 284 | + |
| 285 | + - Learning Data Mining with Python |
| 286 | + |
| 287 | + - Matplotlib for python developers |
| 288 | + |
| 289 | + - Machine Learing with Spark |
| 290 | + |
| 291 | + - Mastering R for Quantitative Finance |
| 292 | + |
| 293 | + - Mastering matplotlib |
| 294 | + |
| 295 | + - Neural Network Programming with Java |
| 296 | + |
| 297 | + - Python Machine Learning |
| 298 | + |
| 299 | + - R Data Visualization Cookbook |
| 300 | + |
| 301 | + - R Deep Learning Essentials |
| 302 | + |
| 303 | + - R Graphs Cookbook second edition |
| 304 | + |
| 305 | + - D3.js By Example |
| 306 | + |
| 307 | + - Data Analysis With R |
| 308 | + |
| 309 | + - Java Deep Learning Essentials |
| 310 | + |
| 311 | + - Learning Bayesian Models with R |
| 312 | + |
| 313 | + - Learning Pandas |
| 314 | + |
| 315 | + - Python Parallel Programming Cookbook |
| 316 | + |
| 317 | + - Machine Learning with R |
| 318 | + |
| 319 | +--- |
| 320 | + |
| 321 | + |
| 322 | + |
| 323 | +## 其他 Miscellaneous |
| 324 | + |
| 325 | + |
| 326 | + |
| 327 | +- [机器学习日报](http://forum.ai100.com.cn/):每天更新学术和工业界最新的研究成果 |
| 328 | + |
| 329 | + |
| 330 | + |
| 331 | +- - - |
| 332 | + |
| 333 | + |
| 334 | + |
| 335 | +## 如何加入 How to contribute |
| 336 | + |
| 337 | + |
| 338 | + |
| 339 | +- 直接pull requests |
| 340 | + |
| 341 | +- 或者到[这里](https://github.com/allmachinelearning/MachineLearning/issues/1)留下你的Github账号我们把你加入贡献者列表 |
| 342 | + |
| 343 | +- PDF等大文件上传方法:登录 http://mega.nz 创建自己的账号,然后可以进行文件共享。原来的公共空间失效了。 |
| 344 | + |
| 345 | +- 之后请在贡献者页面加入自己的信息 |
| 346 | + |
| 347 | + |
| 348 | + |
| 349 | +## 如何开始项目协同合作 |
| 350 | + |
| 351 | +[快速了解github协同工作](http://hucaihua.cn/2016/12/02/github_cooperation/) |
| 352 | + |
| 353 | + |
| 354 | + |
| 355 | +[及时更新fork项目](https://jinlong.github.io/2015/10/12/syncing-a-fork/) |
| 356 | + |
| 357 | + |
| 358 | + |
| 359 | +#### [贡献者 Contributors](https://github.com/allmachinelearning/MachineLearning/blob/master/contributors.md) |
| 360 | + |
| 361 | + |
| 362 | + |
0 commit comments