1.机器学习
斯坦福机器学习CS229课程讲义的中文翻译:https://github.com/Kivy-CN/Stanford-CS-229-CN
机器学习思想演化:http://usblogs.pwc.com/emerging-technology/machine-learning-evolution-infographic/
机器学习算法:http://usblogs.pwc.com/emerging-technology/machine-learning-methods-infographic/
纵观机器学习:http://usblogs.pwc.com/emerging-technology/a-look-at-machine-learning-infographic/
让AI学习更像人——贝叶斯的觉醒:不确定性、高斯过程的重要性:https://www.wired.com/2017/02/ai-learn-like-humans-little-uncertainty/
A Tutorial on Principal Component Analysis:https://arxiv.org/pdf/1404.1100.pdf
pageRank:http://www.changhai.org/articles/technology/misc/google_math.php
Google jupyter:https://www.kaggle.com/getting-started/47096#post271139
贝叶斯定理应用:https://pan.baidu.com/s/1jJYMV5O
集成学习:https://mp.weixin.qq.com/s/zEgan2w9QjAtt0ylzzwHPw
香农熵与信息增益:https://www.youtube.com/watch?v=9r7FIXEAGvs
迁移学习简介:https://machinelearningmastery.com/transfer-learning-for-deep-learning/
2.神经网路
2.1 CNN
机器视角:长文揭秘图像处理和卷积神经网络架构:https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2650728746&idx=1&sn=61e9cb824501ec7c505eb464e8317915
CNN图像分割简史:从R-CNN到Mask R-CNN:http://t.cn/RXpHSab
详解CNN五大经典模型:Lenet,Alexnet,Googlenet,VGG,DRL :https://mp.weixin.qq.com/s/kbHzA3h-CfTRcnkViY37MQ
李理:详解卷积神经网络:http://geek.csdn.net/news/detail/127365
Graph 卷积神经网络:概述、样例及最新进展:https://mp.weixin.qq.com/s?__biz=MzI3MTA0MTk1MA==&mid=2651987895&idx=3&sn=8223f5c491ce6388b13ed7b72ea24f5e&chksm=f1216b46c656e250e953410cc61f152fedf5f7c04f261548c24e463b641b2b20bd5cbcd08003
CNN网络结构:http://cv-tricks.com/cnn/understand-resnet-alexnet-vgg-inception/
2.2 RNN
RNN综述:https://arxiv.org/abs/1801.01078
2.3 科普、资料
Neural Networks for Pattern Recognition :http://cs.du.edu/~mitchell/mario_books/Neural_Networks_for_Pattern_Recognition_-_Christopher_Bishop.pdf
Attention based model 是什么,它解决了什么问题?- 知乎:https://www.zhihu.com/question/36591394
深度学习:随机性不可思议的有效性:https://yq.aliyun.com/articles/64964
深度学习教程:读经典论文学DL系列:https://github.com/sjchoi86/dl_tutorials_10weeks
神经网络激励函数的作用是什么?有没有形象的解释? - 知乎:https://www.zhihu.com/question/22334626
卷积神经网络的数学推导:http://tech.youmi.net/2016/07/163347168.html
深度学习中的注意力机制:https://mp.weixin.qq.com/s/swLwla75RIQfyDDCPYynaw
2.4训练技巧、
神经网络优化算法:https://pan.baidu.com/s/1qZ0IJF2
如何理解深度学习分布式训练中的large batch size与learning rate的关系?:https://www.leiphone.com/news/201710/RIIlL7LdIlT1Mvm8.html
优化神经网络模型结构新方法:https://mp.weixin.qq.com/s/4sntROyvXFGnhUXY-FN67Q
3.算法、编程
100 days of algorithms :https://github.com/coells/100days
知道这20个正则表达式,能让你少写1,000行代码:https://www.jianshu.com/p/e7bb97218946
图解算法复杂度指南:http://algosaur.us/
Google jupyter:https://www.kaggle.com/getting-started/47096#post271139
算法问题与(Python)代码集:https://github.com/qiwsir/algorithm
4 tf/pytorch
斯坦福tensorflow : https://web.stanford.edu/class/cs20si/
tf教程:http://cv-tricks.com/artificial-intelligence/deep-learning/deep-learning-frameworks/tensorflow/tensorflow-tutorial/
http://cv-tricks.com/tensorflow-tutorial/training-convolutional-neural-network-for-image-classification/
https://mp.weixin.qq.com/s/hz_ac9UZuTJKzuSpSuxFvg
香港科技大学PyTorch四日速成教程:
https://github.com/hunkim/PyTorchZeroToAll
https://drive.google.com/drive/folders/0B41Zbb4c8HVyUndGdGdJSXd5d3M
https://pan.baidu.com/s/1cpoyXw
pytorch教程:https://github.com/SherlockLiao/pytorch-beginner
5.自然语言处理
自然语言处理实战:https://www.manning.com/books/natural-language-processing-in-action
如何用 Python 中的 NLTK 对中文进行分析和处理?:https://www.zhihu.com/question/20922994
每个Python程序员都应该知道的35个Python语言特征和编程技巧:http://www.techug.com/post/thirty-python-language-features-and-tricks-you-may-not-know.html
深度学习NLP概览:https://medium.com/htc-research-engineering-blog/notes-for-deep-learning-on-nlp-94ddfcb45723
文本上的算法.pdf:https://github.com/yanxionglu/text_pdf
Podcast: NLP Highlights:https://podfanatic.com/podcast/nlp-highlights
对话系统综述:https://www.paperweekly.site/papers/1446
word embedding综述:http://ruder.io/word-embeddings-2017/index.html
What Is Natural LanguageProcessing?:https://machinelearningmastery.com/natural-language-processing/
五个入门深度学习自然语言处理资源:https://www.jianshu.com/p/371a9dd9bba1
6.图像
计算机视觉到底是啥玩意:http://www.7tin.cn/news/78504.html
OpenCV机器学习》Jupyter Notebook版:https://github.com/mbeyeler/opencv-machine-learning
7.比赛
Kaggle参赛指南之特征工程:https://pan.baidu.com/s/1qYEvDco
https://pan.baidu.com/s/1i57P773
8.数学
基本概率知识汇总表:http://www.wzchen.com/probability-cheatsheet/
如何证明深度网络损失函数是非凸的:https://www.quora.com/How-can-you-prove-that-the-loss-functions-in-Deep-Neural-nets-are-non-convex
如何理解置信度? - 知乎:https://www.zhihu.com/question/20183513
9.其他
这些杀手级应用不太冷——从语义网到知识图谱的回顾:http://blog.memect.cn/wp-content/uploads/2017/01/2017-01-05_%E4%BA%BA%E6%B0%91%E5%A4%A7%E5%AD%A6.pdf
强图灵测试与弱图灵测试:http://blog.sina.com.cn/s/blog_73040b820102x2ll.html
文章千古事,得失寸心知 | 学术人生:https://mp.weixin.qq.com/s/z2xgyTYVdMQTGz5ZIzZ7Gg