资源|深度学习案例和实验分析视频和ITP课程编码

社群用户来源包含：麻省理工学院  斯坦福大学  牛津大学 卡内基梅隆大学  剑桥大学  加州大学伯克利分校  苏黎世联邦理工学院  新加坡国立大学  普林斯顿大学  多伦多大学  帝国理工学院  墨尔本大学  香港科技大学  加州大学洛杉矶分校  清华大学  洛桑联邦理工学院  香港大学  爱丁堡大学  东京大学  香港中文大学  北京大学  复旦大学  武汉大学  南开大学  中科院等数百所名牌大学的研究生、博士以及教授；NVidia  Facebook  Line  微软  IBM  谷歌  Bosch  Amazon  Tesla Motors  百度  华为  英特尔  腾讯  阿里巴巴  蚂蚁金服  科大讯飞  旷视科技  碳云智能  地平线  软银投资  红杉资本等上千家全球一流AI相关企业的工程师以及技术专家。

Machine-Learning

Examples and experiments around ML for upcoming Coding Train videos and ITP course.

Resource attributes

Since resources across the internet vary in terms of their pre-requisites and general accessibility, it is useful to give attributes to them so that it is easy to understand where a resource fits into the wider machine learning scope. Below is a few suggested attributes (please extend):

• creative

• beginner

• intermediate, some pre-requisites

• advanced, many pre-requisites

Table of Contents

• Articles & Posts：

• https://github.com/CodingTrain/Machine-Learning#articles--posts

• Courses

• https://github.com/CodingTrain/Machine-Learning#courses
  

• Examples

• https://github.com/CodingTrain/Machine-Learning#examples
  

• Projects

• https://github.com/CodingTrain/Machine-Learning#projects
  

• Videos

• https://github.com/CodingTrain/Machine-Learning#videos
  

• Resources

• https://github.com/CodingTrain/Machine-Learning#resources
  

• Tools

• https://github.com/CodingTrain/Machine-Learning#tools
  

• Tensorflow

• https://github.com/CodingTrain/Machine-Learning#tensorflow
  

• t-SNE

• https://github.com/CodingTrain/Machine-Learning#t-sne
  

Articles & Posts

1. A Return to Machine Learning
   

   https://medium.com/@kcimc/a-return-to-machine-learning-2de3728558eb#.vlqnbo9yg
   

2. A Visual Introduction to Machine Learning
   

   http://www.r2d3.us/visual-intro-to-machine-learning-part-1/
   

3. Machine Learning is Fun! 

   https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471
   

4. Deep Reinforcement Learning: Pong from Pixels
   

   http://karpathy.github.io/2016/05/31/rl/
   

5. Inside Libratus, the Poker AI That Out-Bluffed the Best Humans 

   https://www.wired.com/2017/02/libratus/?%20imm_mid=0ed017&cmp=em-data-na-na-newsltr_ai_20170206
   

6. Machine Learning in Javascript: Introduction 

   http://burakkanber.com/blog/machine-learning-in-other-languages-introduction/
   

7. Realtime control of sequence generation with character based Long Short Term Memory Recurrent Neural Networks
   

   http://www.iggi.org.uk/assets/IGGI-2016-Memo-A.pdf
   

8. Why is machine learning 'hard'? 

   http://ai.stanford.edu/%7Ezayd/why-is-machine-learning-hard.html
   

9. Unreasonable effectiveness of RNNs
   

   http://karpathy.github.io/2015/05/21/rnn-effectiveness/
   

Courses

1. The Neural Aesthetic @ SchoolOfMa, Summer 2016
   

   http://ml4a.github.io/classes/neural-aesthetic/
   

2. Machine Learning for Musicians and Artists, Kadenze[Scheduled course] 

   https://www.kadenze.com/courses/machine-learning-for-musicians-and-artists-i

   1. Creative Applications of Deep Learning with TensorFlow, Kadenze[Whole Program]
   

   https://www.kadenze.com/programs/creative-applications-of-deep-learning-with-tensorflow
   

3. Coursera - Machine Learning 

   https://www.coursera.org/learn/machine-learning
   

4. Coursera - Neural Networks
   

   https://www.coursera.org/learn/neural-networks
   

Examples

1. A Deep Q Reinforcement Learning Demo 

   http://projects.rajivshah.com/rldemo/
   

2. How to use Q Learning in Video Games Easily
   

   https://github.com/llSourcell/q_learning_demo
   

3. K-nearest 

   https://twitter.com/MaximilianLloyd/status/814942799351185408
   

4. The Infinite Drum Machine
   

   https://aiexperiments.withgoogle.com/drum-machine/view/
   

5. Visualizing the perceptron training algorithm
   

   https://kwichmann.github.io/ml_sandbox/perceptron/
   

Projects

1. Bidirectional LSTM for IMDB sentiment classification
   

   https://transcranial.github.io/keras-js/#/imdb-bidirectional-lstm

2. Land Lines

   https://medium.com/@zachlieberman/land-lines-e1f88c745847#.1157xmhw8
   

3. nnvis - Topological Visualisation of a Convolutional Neural Network
   

   http://terencebroad.com/convnetvis/vis.html
   

4. char-rnn A character level language model (a fancy text generator)
   

   https://github.com/karpathy/char-rnn

Videos

• Reinforcement Learning

1. Artificial Intelligence in Google's Dinosaur (English Sub) 

   https://www.youtube.com/watch?v=P7XHzqZjXQs
   

2. How to use Q Learning in Video Games Easily 

   https://www.youtube.com/watch?v=A5eihauRQvo&feature=youtu.be
   

Evolutionary Algorithms

1. Evolving Swimming Soft-Bodied Creatures
   

   https://www.youtube.com/watch?v=4ZqdvYrZ3ro
   

2. Harnessing evolutionary creativity: evolving soft-bodied animats in simulated physical environments
   

   https://www.youtube.com/watch?v=CXTZHHQ7ZiQ&feature=youtu.be
   

3. Reproduce image with genetic algorithm 

   https://www.youtube.com/watch?v=iV-hah6xs2A
   

Resources

1. Awesome Machine Learning

   https://github.com/josephmisiti/awesome-machine-learning
   

Tools

1. ConvNetJS - Javascript library for training Deep Learning models (Neural Networks) 
   

   http://cs.stanford.edu/people/karpathy/convnetjs/
   

2. RecurrentJS - Deep Recurrent Neural Networks and LSTMs in Javascript
   

   https://github.com/shiffman/recurrentjs
   

3. WORD2VEC
   

   http://technobium.com/find-words-similarity-using-deeplearning4j-word2vec/
   

TensorFlow

1. Projector
   

   http://projector.tensorflow.org/
   

2. Magenta
   

   https://github.com/tensorflow/magenta

3. TensorFlow and Flask

   （https://blog.metaflow.fr/tensorflow-how-to-freeze-a-model-and-serve-it-with-a-python-api-d4f3596b3adc#.96tvigb98_）

   Thanks to @Hebali basic pipeline, minus TensorFlow plus a very basic placeholder function

   http://www.patrickhebron.com/learning-machines/week8.html
   

4. Awesome Tensorflow - curated list of TensorFlow tutorials

   https://github.com/jtoy/awesome-tensorflow
   

Tensorflow posts

1. Big deep learning news: Google Tensorflow chooses Keras

   http://www.fast.ai/2017/01/03/keras/
   

2. Simple end-to-end TensorFlow examples

   http://bcomposes.com/2015/11/26/simple-end-to-end-tensorflow-examples/
   

t-SNE

1. t-SNE 😅

   https://lvdmaaten.github.io/tsne/
   

2. t-SNE 😅

   https://scienceai.github.io/tsne-js/
   

3. An illustrated introduction to the t-SNE algorithm

   https://www.oreilly.com/learning/an-illustrated-introduction-to-the-t-sne-algorithm
   

4. Visualizing Data Using t-SNE 🌈

   https://www.youtube.com/watch?v=RJVL80Gg3lA&list=UUtXKDgv1AVoG88PLl8nGXmw
   

AIjob社

AIjob社：是《全球人工智能》推出的一项免费求职服务。目前与约100家ai企业合作提供近300个工作岗位。有实习，求职和跳槽意向的ai相关开发工程师可发送简历到邮箱：[e-mail]

---

全球人工智能近期经典文章推荐