Machine Learning && Deep Learning Resources

GitHub Special: Data Scientists to Follow & Best Tutorials on GitHub

---

Data Science Tutorials on GitHub

Now,if you are new to GitHub,you would be asking,where do tutorials come in on a platform meant for version control and sharing of codes.Well,because of its niche community,a lot of people have started creating resource repositories on GitHub. Essentially,since the programmers spend a lot of time on GitHub,why not create list of resources they use regularly.
Here’s a compiled list of tutorials on various topics in data science.These resources can be very handy.I suggest you to bookmark these(or watch these on GitHub).

1.Getting started with Data Science

Awesome Data Science:This is an awesome repository if you are to begin with Data Science.Here you’ll find every step that you need to take till the end of your journey.

Data Science Resources:This is another repository of Data Science Tutorials to help you conquer this skill set.You can free to choose any of these,both are equally good.

Text Books in Data Science:If you like to read and refer to books,here is a compiled list of best books on Machine Learning,Data Mining,Statistics,Data Visualization etc.

2.Algorithms

Data Science Algorithms:Here’s a comprehensive overview & explanation of algorithms such as Linear Regression,Logistic Regression,K-Mean Clustering,Random Forest.You’ll also find their worksheets for practice.

Statistics and ML:Here’s a list of tutorials to become efficient in your day to day programming.It covers python pandas,machine learning algorithms,statistics and data visualization.

3.Machine Learning

Scikit Learn:Scikit learn is a python library for machine learning. This repository has everything to offer to help you learn about machine learning in Python.(Hint:Dig Deeper)

Awesome Machine Learning:Here is an ultimate list of tutorials,resources,guides for Machine Learning,Data Analysis,Natural Language Processing,Data Visualization in all the programming languages like Python,R,Java,Go,C++,Swift.Choose accordingly.

Complete Machine Learning:Here’s a collection of tutorials and examples for solving problems using Machine Learning.It consist of beginning to end steps of ML covering stages such as model evaluation,implementation of ML algorithms,data visualization etc.

Parallel Machine Learning:This tutorial is on using scikit learn and iPython for parallel machine learning.Here you’ll find a 2 hours long video from Pycon 2013 with lecture notes and other useful resources.

Machine Learning Cources:Here’s a list of Best Machine Learning Cources in the world.

4.Deep Learning

Caffe:Caffe is a deep learning framework made with expression,speed,and modularity in mind.This repository consist of installation instructions and other recommended tutorials to help you learn this framework properly.

Awesome Deep Learning:Here’s a curated list of tutorials on Deep Learning which includes deep learning courses,free books,videos and lectures,papers and other useful resources to follow.

Deep Learning in Python:Here’s a complete tutorial on implementation of Deep Learning in Python.

Deep Learning in Julia:Mocha is a Deep Learning framework for Julia.This tutorial follows a step by step methodology to be able to introduce this framework in the best possible manner.

Recurrent Neural Networks:Here’s a awesome list of dedicated resources for RNN.If you have longed to curate the resources for RNN,you’ve like to stop here and take a glance.This guide consists of codes,lectures,book and resources on multiple applications of RNN.

Top 30 Data Scientists to Follow on GitHub

Here’s a compiled list of most influential data scientists on GitHub to follow.These data scientists are experts in their respective field which ranges from python,machine learning,neural nets,data visualization,deep learning,data science etc.

1.Sebastian Raschka (Machine Learning,Data Visualization)

2.Randy Olson (Python-Data Analysis,Matplotlib,Bokeh)

3.Hilary Mason (Chief Data Scientists at Bitly)

4.Mike Bostock (D3,Data Visualization)

5.Prakhar Srivastav (Python,Algorithms)

6.Andreas Mueller (Machine Learning,Python)

7.Wes Mckinney (Author of Python for Data Analysis)

8.Jake Vanderplas (Machine Learning,Data Visualization)

9.Mathieu Blondel (Machine Learning,Neural Networks)

10.Gael Varoquaux (Machine Learning,Statistics,Python)

11.Oliver Grisel (Machine Learning,Deep Learning)

12.Andrej (Deep Learning,Neural Networks,SVM)

13.Micheal Nielsen (Neural Networks,Deep Learning)

14.Heather Arthur (Neural Networks,Javascript)

15.Allen Downey (Python,Algorithms)

16.Davies Liu (Apache Spark,Python)

17.Julia Evans (Machine Learning,Python)

18.Jeff L (R Programming,Data Analysis)

19.John Myles White (Julia,Machine Learning)

20.Thomas Wiecki (Python,Bayesian Analysis)

21.Brian Caffo (John Hopkins University)

22.Roger D Peng (John Hopkins University)

23.Stefan Karpinski (Julia)

24.Pete Skomoroch (Machine Learning,Big Data,Python)

25.Mike Dewar (Python,D3,Javascript)

26.Hadley Wickham (Statistics,Data Analysis,Data Visualization)

27.Romain Francois (R Programming)

28.Justin Palmer (D3,Data Visualization)

29.Jason Davies (D3,Data Visualization)

30.Cameron Davidson Pilon (Python,Algorithms)

[转]http://www.analyticsvidhya.com/blog/2015/07/github-special-data-scientists-to-follow-best-tutorials/