--- title: Machine Learning - Resources tags: CoderSchool --- ![](https://i.imgur.com/0AUxkXt.png) # Machine Learning Resources The following is a list of free or paid online courses, blog posts, on machine learning, statistics, data-mining, etc. ## Courses ### [Machine Learning (Stanford University, Andrew Ng)](https://www.coursera.org/learn/machine-learning) - Andrew Ng's course. Recommended for anyone who wants to start learning Machine Learning. - Math approach, easy to understand. - Covers basic Machine Learning algorithms. - Theories + Practice in Matlab. ### [Neural Networks for Machine Learning (University of Toronto)](https://www.youtube.com/watch?v=cbeTc-Urqak&list=PLYvFQm7QY5Fy28dST8-qqzJjXr83NKWAr) - Very basic concept and detailed of NN in Machine Learning. - Explained by intuition, not much of Math. - Theories 100%. ### [Deep Learning Specialization (by Andrew Ng, deeplearning.ai)](https://www.coursera.org/specializations/deep-learning) - Recommended for anyone wanting to start with Deep Learning. - Because it is Andrew Ng's. ### [Intro to Deep Learning (MIT)](http://introtodeeplearning.com/) - Comprehensive but not too much in details. - Including basic concepts and **big projects** - Theories + Projects ### [Stanford's CS20 Tensorflow for Deep Learning Research](http://web.stanford.edu/class/cs20si/) - Comprehensive of learning Tensorflow for Deep Learning - Instructor: Huyen Chip - Theories (Slides) + Assignments ### [fast.ai](https://www.fast.ai/) - deep learning MOOC - Including practical and also theoretical materials. - Top-down approach ### [Machine Learning Specialization (University of Washington)](https://www.coursera.org/specializations/machine-learning) - But the length of the course is quite long - Contains Supervised (Classification, Regression) and Unsupervised learning (Clustering and Retrieval) - Theories and Case studies ### [Machine Learning Course - Oxford](https://www.cs.ox.ac.uk/people/nando.defreitas/machinelearning/) - Fundamental components of Deep Learning + CNN + RNN + Reinforcement Learning - Lecture slides and video recordings. - Practical part using Torch. - Quite heavy on Math ### [Stanford's CS231n: CNNs for Visual Recognition](https://www.youtube.com/watch?v=vT1JzLTH4G4&index=1&list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv) - Spring 2017 iteration, [Course website](http://cs231n.github.io/) has supporting material. - Very detailed about CNN for Computer vision - Including videos, assignments, and very good materials on Course website. - Requires strong background of Math. ### [Machine Learning Crash Course (Google) - with Tensorflow](https://developers.google.com/machine-learning/crash-course/) - free - Introductory (quite basic) level, appropriate for beginners - Prerequisites: Mastery of Linear Algebra, Proficiency in basic programming - Including videos, reading materials - **Plus: Exercise to check understanding, notebook to practice programming Tensorflow, Playground to interact with NN**. - **Plus: Include interactive examples within lectures.** ### [Machine Learning Mini Bootcamp Course (LambdaSchool)](https://lambdaschool.com/courses/data-science/intro/) - Include lectures as jupyter notebook - Include Coding and Sprint challenges. - Generic theories and practices. - Ranging from Math to ML models to NN to Reinforcements. ### [Microsoft Professional Program for Artificial Intelligence](https://academy.microsoft.com/en-us/professional-program/tracks/artificial-intelligence/) - Very comprehensive course with essential concepts inlcuding Math and Research skills - Using NLTK - MS's Deep Learning framework. - Including Homework, Lecture videos, and Reading materials ### [Open Machine Learning Course](https://github.com/Yorko/mlcourse.ai) with [articles](https://medium.com/open-machine-learning-course) on Medium - Comprehensive Notebooks and blog posts on Medium - Can be used for References / Additional Reading Material ### [Machine Learning A-Z (Udemy)](https://www.udemy.com/machinelearning/) - Hands-On Python & R In Data Science - Popular course on Udemy. - Introductory level for ML concepts, **very intuitive explanation.** - Including Lab to practice. ## Books ### [Introduction to Applied Linear Algebra](http://vmls-book.stanford.edu/vmls.pdf) - A good introduction to Applied linear Algebra from Standford. This can be good start if you want a solid knowledge of linear algebra before learning ML. ### [Introduction to Probability](https://drive.google.com/file/d/1VmkAAGOYCTORq1wxSQqy255qLJjTNvBI/view) - A great introduction to Probability concept, which is essential for any Machine learning or data related techniques. ### [ESL](https://web.stanford.edu/~hastie/ElemStatLearn/printings/ESLII_print12.pdf) and [ISL](http://www-bcf.usc.edu/~gareth/ISL/ISLR%20Seventh%20Printing.pdf) - Beginner (ISL) and Advanced (ESL) presentation to classic machine learning from world-class stats professors. ### [Foundation of Data Science](https://www.microsoft.com/en-us/research/wp-content/uploads/2017/11/book-June-14-2017pdf.pdf) - Very comprehensive overview of Data Science essentials. ### [Deep Learning by Ian Goodfellow](https://www.deeplearningbook.org/) - An advanced but very essential if you want to have a low-level understanding of Deep Learning concept. ## Blog Posts/Documentations/Tutorials ### [Pytorch Documentation](https://pytorch.org/tutorials/) - Very comprehensive documentation of Pytorch. ### [Pytorch Tutorials](https://pytorch.org/docs/stable/index.html) - Examples and tutorials from Pytorch team. ### [Computational Linear Algebra for Coders](https://github.com/fastai/numerical-linear-algebra/blob/master/README.md) - This course is focused on the question: How do we do matrix computations with acceptable speed and acceptable accuracy? ### [Linear Algrebra for Reference by Standford](https://sgfin.github.io/files/notes/CS229_Linear_Algebra.pdf) - Standford team's great note of Linear Algebra in CS229 course. If you want a quick overview but still comprehensive enough, this is the one. ### [Matrix Calculus for Deep Learning](https://explained.ai/matrix-calculus/index.html) - Matrix calculus is a must for every Deep Learning practitioner. This is for you if you want to get a fast start with Matrix Calculus. ### [Lecture notes from Andrew Ng's intro to ML](https://sgfin.github.io/files/notes/CS229_Lecture_Notes.pdf) - If you want a good mathematical perspective of Machine learning concepts, this lecture note of course CS229 is the one. ### [Natural Lanaguage Processing with DL notes - CS224](https://sgfin.github.io/files/notes/cs224n-2017-merged.pdf) - Fantastic course notes on Deep Learning for NLP from Stanford ### [Neubig's Neural Network for NLP](http://www.phontron.com/class/nn4nlp2018/schedule.html) - Great course from CMU's Graham Neubig. With lecture videos [here](https://www.youtube.com/playlist?list=PLbdKUKMAnh9Qqs5uwEBDfRb_L3YaLbRKq) ## Cheatsheet ### [Computer Science Theory Cheatsheet](https://www.tug.org/texshowcase/cheat.pdf) - Comprehensive summary of necessary mathematics and computer science theories, ranging from graph theory to calculus, probability, ... ### [SQL Joins Cheatsheet](https://sgfin.github.io/files/cheatsheets/SQL_joins.png) - Graphical description of classifc SQL joins ### [Python Pandas Cheatsheet](https://sgfin.github.io/files/cheatsheets/Python_cheatsheet_pandas.pdf) - Cheatsheet for Python's data wrangling and manipulating, Pandas. ### [Python Numpy Cheatsheet](https://sgfin.github.io/files/cheatsheets/Python_cheatsheet_numpy.pdf) - Cheatsheet for Python's efficient numerical package, Numpy. ### [Python Keras Cheatsheet](https://sgfin.github.io/files/cheatsheets/Python_Keras_Cheat_Sheet.pdf) - Cheatsheet for Python's high-level API of Deep learning, Keras. ### [Python Sklearn Cheatsheet](https://sgfin.github.io/files/cheatsheets/Python_cheatsheet_scikit.pdf) - Cheatsheet for Python's Machine learning package, sklearn. ### [Python Seaborn Cheatsheet](https://seaborn.pydata.org/tutorial.html) - Tutorials and examples for Python visualization library, Seaborn. ### [Python Pytorch Cheatsheet](https://pytorch.org/tutorials/beginner/ptcheat.html) - World-class quality cheatsheet from Pytorch, a deep learning library. ### [Probability Cheatsheet](https://sgfin.github.io/files/cheatsheets/probability_cheatsheet_blackwhite.pdf) - Comprehensive overview of Probability concepts with illustrations. ### [Standford Machine Learning Cheatsheet](https://sgfin.github.io/files/cheatsheets/cs229_2018_cheatsheet.pdf) - A great cheatsheer from Standford team with essential knowledge about Machine learning concept with examples and illustrations ## References - [Awesome Machine Learning](https://github.com/josephmisiti/awesome-machine-learning/blob/master/courses.md) - [Machine Learning Resources](https://sgfin.github.io/learning-resources/?fbclid=IwAR0MwKLjjv_Dpgw8w7ofWbVfHZb5AV0LA-ZAU47k0iLuredsQMSzthkVBps) ## Miscellanious - [KDE](https://mathisonian.github.io/kde/) -