The purpose of this post is to recommend the best resources I've found that will get one competent in Machine Learning/ Artificial Intelligence in an efficient and focused way. I've worked as a researcher in machine learning, and have use machine learning methods at my occupation.
100 Page Machine Learning Book
A small book that boils to the essentials of machine learning while still showing the mathematical foundations: well-known algorithms, evaluation of metrics, model selection, etc. Implement every algorithm in this book to truly understand what's going on, which the next recommendation will help you do.
Data Science From Scratch
Great, you know many of the well known algorithms. However, you don't really know anything unless you've displayed competency through implementation. That is what this book is all about. It will guide you on implementing many of the algorithms you've seen in the previous book using Python. Try your best to do it yourself of course.
Mathematics of Machine Learning
Basic competency of the mathematics of machine learning is needed to know what's going on in machine learning algorithms. It will allow you to develop new ones if you become a researcher. Linear Algebra, Probability Theory, Optimization Theory, etc are all the foundations of modern machine learning.
If you need structure, this is the course I followed that uses Mathematics of Machine Learning:
Even if you have the best model, what good is it if you can't get it out to customers for them to use? This resource goes over the processes of serving machine learning models to customers.
100 Page Machine Learning Book
A small book that boils to the essentials of machine learning while still showing the mathematical foundations: well-known algorithms, evaluation of metrics, model selection, etc. Implement every algorithm in this book to truly understand what's going on, which the next recommendation will help you do.
Data Science From Scratch
Data Science from Scratch, 2nd Edition
To really learn data science, you should not only master the tools—data science libraries, frameworks, modules, and toolkits—but also understand the ideas and principles underlying them. Updated for Python 3.6, … - Selection from Data Science from Scratch, 2nd Edition [Book]
www.oreilly.com
Great, you know many of the well known algorithms. However, you don't really know anything unless you've displayed competency through implementation. That is what this book is all about. It will guide you on implementing many of the algorithms you've seen in the previous book using Python. Try your best to do it yourself of course.
Mathematics of Machine Learning
Mathematics for Machine Learning
Companion webpage to the book “Mathematics for Machine Learning”. Copyright 2020 by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong. Published by Cambridge University Press.
mml-book.github.io
Basic competency of the mathematics of machine learning is needed to know what's going on in machine learning algorithms. It will allow you to develop new ones if you become a researcher. Linear Algebra, Probability Theory, Optimization Theory, etc are all the foundations of modern machine learning.
If you need structure, this is the course I followed that uses Mathematics of Machine Learning:
The Full Stack
News, community, and courses for people building AI-powered products.
fullstackdeeplearning.com
Even if you have the best model, what good is it if you can't get it out to customers for them to use? This resource goes over the processes of serving machine learning models to customers.
Last edited: