Machine Learning and Deep Learning Courses
A collection of the latest machine learning and deep learning courses.
If you follow me on Twitter, you will know that I have been curating and sharing some of the most recent machine learning, natural language processing (NLP), and deep learning courses that have been publicly released. I have completed the majority of these courses and some I am currently reviewing.
At the request of some people, I have decided to write this blog post so that it is easier to maintain and bookmark the complete collection of courses. Here they are:
Includes a great introduction to deep learning starting with the machine learning basics moving into more core topics like optimization. (by Sergey Levine)
This is one of the most recent deep learning courses focusing on hot topics like self-supervised learning, transformers, and energy based models. (by Alfredo Canziani)
This course is focused on the popular free book available on the d2l.ai website. If you have been studying the book, this set of lectures will come in handy. (by Alex Smola)
If you are not too familiar with natural language processing (NLP) concepts, this is a great place to start. It provides short and accessible summaries of some of the most important techniques used to solve NLP problems. (by Machine Learning University)
Another playlist that will be helpful for NLP students is the one provided by Dan Jurafsky and Chris Manning.
This course covers topics related to how neural networks are used in natural language processing (NLP). (by Graham Neubig)
This has been one of the most popular NLP courses for some time now. It focuses on the use of the latest deep learning techniques applied to NLP problems. (by Chris Manning)
The NLP courses above focus heavily on the theory. To get the practical side of NLP, this fast.ai course will be a great place to start. (by Rachel Thomas)
Graham Neubig also provides another great course that focuses on multilingual NLP. Topics range from data annotation to code switching to low resource automatic speech recognition. (by Graham Neubig)
This course focuses heavily on the latest techniques in deep learning for computer vision tasks. From attention mechanism to generative models. (by Justin Johnson)
Focuses on the use of deep learning-based architectures for reinforcement learning problems. (by Sergey Levine)
While most of the courses above focus heavily on theory, this course specifically focuses on the ecosystem of tools used to develop and deploy deep learning models. (by Josh Tobin, Pieter Abbeel, Sergey Karayev)
This is another course by fast.ai focusing on a coder-first approach to deep learning. (by Jeremy Howard)
A machine learning course about how to apply ML algorithms in practice. (by Volodymyr Kuleshov)
This is an ongoing course teaching how to build a production-grade product through ML techniques and tools. (by Made with ML)
This is not an exhaustive list of courses. There are obviously many other great courses out there. I can only comment on the ones I have reviewed and completed. If you have further recommendations, please include them in the comments section.
There are plenty of courses to choose from. You probably only need to start with a few of them. Taking all these courses at once is not a good strategy as there is a lot of overlap. Different courses are taught in different styles and levels. You should first look at the syllabus and decide what level is right for you.
I try to regularly maintain this guide. To get regular updates on new ML and NLP resources, follow me on Twitter.