Its one of those buzzwords that we’ve all heard whether we’re programmers or not: machine learning. Unlike other trends in the past, machine learning isn’t a fad, it really is the future.
As AIs become more and more sophisticated, programmers need to get up to speed on what it is, how it works, and the latest trends in the field. Fortunately, these 13 free resources offer an excellent introduction to machine learning so you can get started with some basic machine learning tutorials right away.
Before you begin to study the machine learning basics, make sure you’re familiar with the python scripting language. It is the most popular scripting language for data science and machine learning and will be required to get the most out of these resources.
SEE ALSO: THIS BUNDLE WILL SHOW YOU HOW TO PROGRAM MACHINE LEARNING ALGORITHMS WITH PYTHON
Don’t know python? Don’t worry, whatever programming or scripting language you are familiar with, picking up python shouldn’t be too difficult, as it is one of the more forgiving languages to learn. Read on through these resources and find out what specific topics you need to learn more about before continuing on, or just give it a go anyway—you might just learn a little python in the process.
These online texts and tutorials will give you a solid foundation in the topics, theories, and languages used in machine learning.
These are great machine learning tutorials for starting out in that Kaggle covers all the essentials you need to know about data science in order to get started with machine learning. Remember, machine learning is about training a machine on very large data sets, so knowing data science is an essential step in your introduction to machine learning.
This is easily one of the best “books” on python and machine learning you are going to find. If you aren’t all that hot with python just yet, spend time with this resource and you’ll be data-scrapping websites in no time. It also includes sample code to go along with the text material so you can refer to the sample work when needed.
An online text that provides an introduction to machine learning basics while also giving a primer of deep learning theory. This approach guides you through the implementation of the different concepts so be prepared to write a lot of code, but its an incredibly useful resource overall.
This is a great way to get into the meat and bones of machine learning—specifically deep learning, the kind that lets Netflix know what movies to recommend to you and how to identify the content of image files. If you’re ready to hit the ground running, this site is where you ought to be.
Deep Learning is put out by MIT Press and written by Ian Goodfellow, Yoshua Bengio, and Aaron Courville, and it is one of the best books you will ever find on deep learning. The publisher has made the book available for free as an HTML website, so make sure to bookmark it and work your way through the best text on deep learning out there.
These video resources are an excellent place to go if you want to learn more than the basics and get into some of the specific topics of machine learning.
MIT offers a whole host of free resources and the MIT Deep Learning page is no exception. Here, you’ll find dozens of videos of lectures, talks, interviews, and more on the various topics in machine learning and deep learning. This is definitely a must-bookmark page for anyone looking for more than just the introduction to the machine learning basics we’ve seen so far.
This site features video lectures from some of the top machine learning professionals given at the Montreal Deep Learning Summer School for the past couple of years. These videos—companion slides to the videos are available as well—are primarily about more intermediate theory topics than the basics, but if you feel you’re ready, dive right in.
These resources will help you learn how to parse through large sets of text data to find the meaning in all the noise.
This online text is available via HTML and is an essential text for learning natural language processing using python. It utilizes Python’s Natural Language Toolkit which is the API library that your natural language processing education will rely on going forward, so best to learn it right away.
This is a collection of Jupyter notebooks that accompany Jon Krohn’s tutorial videos on natural language processing using deep learning. Some of the things he covers include preprocessing natural language data for machine learning apps, transforming natural language into numerical expressions, making predictions with models trained used deep learning, and much more.
This is a set of machine learning tutorials based on Jupyter notebooks fromInsight AI’sEmmanuel Ameisen. It breaks down different topics in machine learning to the basic tasks required to achieve your goal and provides helpful diagrams to help you follow along.
This machine learning tutorial really only does one thing, it teaches you how to build an LSTM for Keras language modeling. It is a short tutorial, but you can finish it off in a day or two and can be used right out the gate to begin processing your own large text data sets for prediction modeling.
These courses are free to access (with limitations) and provide university-level instruction on machine learning topics.
This is an open-access university-level course on introductory AI development from one of the top universities in the world. There’s no college credit, no one will grade your work, and access to some material is limited, but the essential materials you need to get started with AI machine learning are all here.
This open access course offers instruction on another track of machine learning we haven’t talked about much, reinforcement learning. This important method of machine learning is a useful tool to have in your machine learning toolbelt and this course from University College London is a great place to learn what you need to know.