# Machine_Learning_Study_Path **Repository Path**: marcel0718/Machine_Learning_Study_Path ## Basic Information - **Project Name**: Machine_Learning_Study_Path - **Description**: 机器学习过程中所看的书,视频和源码 - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-05-10 - **Last Updated**: 2020-12-19 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README 从入门到进阶,所用到机器学习资料,包括书、视频、源码。 # 1.视频: ## 1.1 吴恩达老师机器学习课程: * [Coursera](https://www.coursera.org/learn/machine-learning) * [网易云课堂](http://study.163.com/course/introduction/1004570029.htm?courseId=1004570029) * [英文笔记](https://github.com/linxid/Machine_Learning_Study_Path/tree/master/%E7%AC%94%E8%AE%B0/%E5%90%B4%E6%81%A9%E8%BE%BE%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E7%AC%94%E8%AE%B0) * [中文笔记、字幕](https://github.com/fengdu78/Coursera-ML-AndrewNg-Notes) ## 1.2 吴恩达 深度学习课程 * [Coursera](https://www.coursera.org/specializations/deep-learning) * [网易云课堂](http://mooc.study.163.com/smartSpec/detail/1001319001.htm) * [笔记](http://www.ai-start.com/dl2017/) ## 1.3 斯坦福CS231n:Convolutional Neural Networks for Visual Recognition * [官网](http://cs231n.stanford.edu/) * [网易云课堂](http://study.163.com/course/introduction/1003223001.hm) ## 1.4 fast.ai * [官网](http://www.fast.ai/) * [Part1:Practical Deep Learning For Coders](http://course.fast.ai/) * [Part2: Cutting Edge Deep Learning For Coders](http://course.fast.ai/part2.html) ## 1.5 [百度PaddlePaddle公开课:](http://ai.baidu.com/paddlepaddle/openCourses) * 机器学习入门 * 机器学习模型 * 深度学习基础 ## 1.6 徐亦达老师机器学习课程: * [官网](https://www.uts.edu.au/staff/yida.xu) * [Github](https://github.com/roboticcam/machine-learning-notes) * [哔哩哔哩](https://www.bilibili.com/video/av12802062?p=2) * [百度云](https://pan.baidu.com/s/1PW0vuhHgMg3xAWRSoHoXbw#list/path=%2F) ## 1.7 李宏毅深度学习课程 * [官网](http://speech.ee.ntu.edu.tw/~tlkagk/courses.html) * [哔哩哔哩](https://www.bilibili.com/video/av9770302/) ## 1.8 谷歌机器学习速成 * [课程](https://developers.google.cn/machine-learning/crash-course/prereqs-and-prework) * [练习](https://developers.google.cn/machine-learning/crash-course/exercises) * [术语库](https://developers.google.cn/machine-learning/crash-course/glossary) # 2.书籍: ## 2.1 Keras: * [《Deep Learning with Python》](https://www.amazon.cn/dp/1617294438/ref=sr_1_1?s=books&ie=UTF8&qid=1541668924&sr=1-1&keywords=deep+learning+with+python) 难度:低;推荐:☆☆☆☆☆ * [《Deep Learning with Keras》](https://www.packtpub.com/big-data-and-business-intelligence/deep-learning-keras) 难度:低;推荐:☆☆☆☆ ## 2.2 TensorFlow: * [《Hands-On Machine Learning with Scikit-Learn and TensorFlow》](http://shop.oreilly.com/product/0636920052289.do) 难度:中;推荐:☆☆☆☆☆ * [《Learning TensorFlow》](https://www.amazon.com/Learning-TensorFlow-Guide-Building-Systems/dp/1491978511) * [《TensorFlow Machine Learning cookbook》](https://www.packtpub.com/big-data-and-business-intelligence/tensorflow-machine-learning-cookbook) 难度:中;推荐:☆☆☆☆☆ ## 2.3 NLP: * [《Deep Learning in Natural Language Processing》](https://www.springer.com/us/book/9789811052088) * [《Natural Language Processing with TensorFlow》](https://www.packtpub.com/application-development/natural-language-processing-tensorflow) * [《Mastering Natural Language Processing with Python》](https://www.packtpub.com/big-data-and-business-intelligence/mastering-natural-language-processing-python) * [《Text Analytics with Python》](https://www.apress.com/la/book/9781484223871) ## 2.4 机器学习: * [《统计学习方法》](https://www.amazon.cn/dp/B007TSFMTA/ref=sr_1_1?s=books&ie=UTF8&qid=1541668369&sr=1-1&keywords=%E7%BB%9F%E8%AE%A1%E5%AD%A6%E4%B9%A0) 难度:中;推荐:☆☆☆☆☆ * [《Pattern Recognition and Machine Learning》](https://www.amazon.cn/dp/0387310738/ref=sr_1_1?s=books&ie=UTF8&qid=1541668434&sr=1-1&keywords=prml) 难度:高;推荐:☆☆☆☆☆ * [《机器学习实战》](https://www.amazon.cn/dp/B00D747PTK/ref=sr_pyc1?s=books&ie=UTF8&qid=1541669024&sr=1-1-pinyin&keywords=jiqixuexishizhan) 难度:低;推荐:☆☆☆☆ * [《Machine Learning yearning》](http://www.mlyearning.org/) * [《美团机器学习实战》](http://item.jd.com/12414240.html?dist=jd) * [《集体智慧编程》](https://www.amazon.cn/dp/B00UI93JD8/ref=sr_1_1?s=books&ie=UTF8&qid=1541669086&sr=1-1&keywords=%E9%9B%86%E4%BD%93%E6%99%BA%E6%85%A7%E7%BC%96%E7%A8%8B) 难度:低;推荐:☆☆☆☆ * [《百面机器学习 算法工程师带你去面试》](https://item.jd.com/12401859.html) ## 2.5 深度学习: * [《Deep Learning》 中文版](https://www.amazon.cn/dp/B073LWHBBY/ref=sr_1_1?s=books&ie=UTF8&qid=1541668263&sr=1-1&keywords=deep+learning) 难度:高;推荐:☆☆☆☆☆ * [《神经网络与深度学习》](http://neuralnetworksanddeeplearning.com/) 难度:中;推荐:☆☆☆☆ * [《Deep Learning with python A Hands on Introduction》](https://www.amazon.cn/dp/1484227654/ref=sr_1_1?ie=UTF8&qid=1541750979&sr=8-1&keywords=Deep+Learning+with+Python%3A+A+Hands-on+Introduction) 下载链接:https://pan.baidu.com/s/12w9NjsnOSPUAX5U4BVvBIg 提取码: hucw # 3.框架 |基础框架 | 机器学习|深度学习| |--|--|--| |[pandas](http://pandas.pydata.org/index.html),[imbalanced-learn](http://contrib.scikit-learn.org/imbalanced-learn/stable/index.html)|[sklearn](http://sklearn.apachecn.org/),[LightGBM](http://lightgbm.apachecn.org/cn/latest/index.html)|[TensorFlow](https://www.tensorflow.org/api_docs/python/),[Keras](http://keras-cn.readthedocs.io/en/latest/)| |[xLearn](http://xlearn-doc.readthedocs.io/en/latest/start.html)| [XGBoost](http://xgboost.readthedocs.io/en/latest/get_started/) ,[CatBoost](https://tech.yandex.com/catboost/doc/dg/concepts/python-installation-docpage/)|[PyTorch](https://pytorch.org/),[PaddlePaddle](http://staging.paddlepaddle.org/docs/develop/documentation/zh/getstarted/index_cn.html)| # 4. 机器学习博客: * [Open AI](https://blog.openai.com/): 由Elon Musk提出建立的一个人工智能非营利组织,定期发布有关自然语言处理,图像处理和语音处理等先进人工智能技术的研究。 * [Distill](https://distill.pub/): 编辑和策展团队由来自Google Brain,DeepMind,Tesla和其他着名组织的科学家组成。致力于清晰的解释机器学习。 * [BAIR 博客](https://bair.berkeley.edu/blog/): 加州大学伯克利分校的伯克利AI研究(BAIR)小组设立。BAIR博客旨在传播BAIR在人工智能研究方面的研究成果,观点和最新情况。 * [DeepMind](https://deepmind.com/blog/?category=research): DeepMind的大名,我想很多人已经知道了。 * Andrej Karpathy的博客: 原博客:http://karpathy.github.io/ Medium:https://medium.com/@karpathy 特斯拉的人工智能总监,很多人也许看过他的博客,但是不知道这个人。现在他已经转战Medium,很多文章发布在Medium。 * [Colah的博客](http://colah.github.io/): Christopher Olah是Google Brain的研究科学家。旨在用简单的方式解读神经网络。 * [WildML](http://www.wildml.com/): 博主同样来自Google Brain,写作的主要焦点是深度学习。 * [Ruder的博客](http://ruder.io/): 博主是一位博士生,博客以深度学习和自然语言处理为主。 * [FAIR博客](https://research.fb.com/blog/): FAIR的大名就不多讲了,我想很多人知道,很多精彩论文出自FAIR,博客讨论了人工智能,深度学习,机器学习,计算机视觉及其在Facebook自研产品上的实际应用。 * [Adit Deshpande的博客](https://adeshpande3.github.io/) UCLA的一名本科生(自愧不如啊),很多内容为初学者准备,由浅入深,层层递进。 * [inFERENCe的博客](https://www.inference.vc/): 剑桥的博士,与Twitter Cortex合作。他撰写了关于概率推理,生成模型,无监督学习。 * [Andrew Trask的博客](http://iamtrask.github.io/): 非常推荐,博主是DeepMind的研究科学家和博士。简单列几篇他的博客: [Tutorial: Deep Learning in PyTorch](http://iamtrask.github.io/2017/01/15/pytorch-tutorial/) [Anyone Can Learn To Code an LSTM-RNN in Python (Part 1: RNN)](http://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/)