Machine Learning (ML)

Machine Learning is all about learning patterns (i.e., functions and relations) from data (i.e., data points). Machine Learning (called by computer scientists and programmers) is also known as Statistical Learning (called by statisticians), Pattern Recognition (called by engineers), Curve Fitting (called by mathematicians), and Predictive Analytics (called by business persons). Machine Learning is the algorithmic component of Data Mining (called by database scientists) and Data Science (called by data scientists).

Deep learning, a subfield of machine learning, is currently the hottest subfield of computer science. This has become possible due to three reasons:
(a) [Power.] Deep learning algorithms can possibly approximate any arbitrary hidden function,
(b) [Speed.] Deep learning algorithms are fast due to the use of GPUs and distributed algorithms, and
(c) [Accuracy.] Deep learning algorithms can reduce errors more than other machine learning algorithms.

Video Courses	(Nice Videos) Josh Starmer's StatQuest - Youtube Playlist, All Videos List (Mindblowing Videos) 3Blue1Brown's Neural Networks - Youtube Playlist Google's Machine Learning Crash Course - https://developers.google.com/machine-learning/crash-course/ml-intro Geoffrey Hinton's Deep Learning Course - Youtube Playlist
Learn by Doing	Stanford University Undergrad Projects - CS229, CS230 Colaboratory - http://colab.research.google.com/ Seedbank - https://research.google.com/seedbank/
Paid Books	[FMLPDA] Fundamentals of Machine Learning for Predictive Data Analytics. John D. Kelleher, Brian Mac Namee, and Aoife D'Arcy. MIT Press. 1st Edition. [FMLPDA] Hands-on Machine Learning with Scikit-Learn and TensorFlow. Aurélien Géron. O'Reilly. 1st Edition.
Free Books (Legal)	[WB] The Wiki Book on Machine Learning. Good People. [PDSH] Python Data Science Handbook. Jake VanderPlas. O'Reilly. [ISL] An Introduction to Statistical Learning. Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani. Springer. 2nd Edition. [NNDL] Neural Networks and Deep Learning. Michael A. Nielsen. Determination Press. [PGDM] A Programmer's Guide to Data Mining. Ron Zacharski. [ESL] The Elements of Statistical Learning. Trevor Hastie, Robert Tibshirani, and Jerome Friedman. Springer. 2nd Edition. [DL] Deep Learning. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. MIT Press. 1st Edition. [RL] Reinforcement Learning. Richard S. Sutton and Andrew G. Barto. MIT Press. 2nd Edition. [PRML] Pattern Recognition and Machine Learning. Christopher M. Bishop. Springer. More Books
Summary Articles	[Deep Learning] Different Types of Neural Networks. Asimov Institute.
Research Papers	[CSUR 2019] - A Survey on Deep Learning: Algorithms, Techniques, and Applications
Cheatsheets	Graphic Design - https://sgfin.github.io/files/cheatsheets/graphic_design.pdf ML algorithm estimator - https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html Python's numerical package, NumPy - https://sgfin.github.io/files/cheatsheets/Python_cheatsheet_numpy.pdf Python's data wrangling package, Pandas - https://sgfin.github.io/files/cheatsheets/Python_cheatsheet_pandas.pdf Python's ML package, Scikit-Learn - https://sgfin.github.io/files/cheatsheets/Python_cheatsheet_scikit.pdf Python's NN package, Keras - https://sgfin.github.io/files/cheatsheets/Python_Keras_Cheat_Sheet.pdf
Tutorials	Scikit-Learn Documentation - https://scikit-learn.org/stable/_downloads/scikit-learn-docs.pdf Scikit-Learn Examples - https://scikit-learn.org/stable/auto_examples/index.html Scikit-Learn User Guide - https://scikit-learn.org/stable/user_guide.html
Datasets	Google Dataset Search - https://toolbox.google.com/datasetsearch Kaggle Dataset Search - https://www.kaggle.com/datasets US Public Data - https://www.data.gov/ US Public Data Visualized - https://datausa.io/