Carnegie Mellon's introductory graduate-level machine learning course, taught in past offerings by Andrew Moore and Tom Mitchell, with lecture notes, homeworks, and readings posted publicly. The course covers the core algorithms and theory of machine learning.

Commenters call it a fantastic course, especially for its exercises, and note that its lectures and materials are freely available online.

What commenters said (2)

1. Strongly recommendsquantombone2014in “Google VP named Dean of Carnegie Mellon’s School of Computer Science”

   I remember taking Moore's grad level Machine Learning course in 2005 (was co-taught with Tom Mitchell). I have great memories from that course, especially interactions with my fellow robotics friends: Mark Palatucci (now a co-founder and officer at Anki), Geoffrey Hollinger (now a professor at Oregon State), and Jon Huang (now a postdoc at Stanford).

   Moore gave us a very intuitive way to understand machine learning algorithms, and Mitchell gave us a more theoretical account. I remember working with Jon Huang on a Latent Dirichelet Allocation algorithm implementation for the final project. It was a lot of fun and very intense at the same time. Such great memories!

   Moore have me an excellent foundation of concepts, and I'm really glad for CMU to have such a respectable figure back on campus.

   I expect great things for CMU, especially Robotics and Machine Learning!

2. Recommendseykanal2016in “Statistical Machine Learning, Spring 2016”

   For those of you interested in this stuff, this course (10-702) is the second in a series. The 10-701 course, "Intro to Machine Learning", is a fantastic course as well, even if just for the exercises. This year's version is here [1], you can find lecture notes, links to lectures posted on YouTube, homeworks, readings, etc. You can also just google "10-701" and see a lot of previous course websites with similar material.

   For what it's worth, nowadays, the problem isn't availability of learning material. This stuff is being literally given away. Its that you, the student, has to really dedicate time to the material. The first homework assignment for the 10-701 class wasn't even that difficult (relatively speaking) and it still took me over ten hours to finish. Persevere! It's worth it.

   [1]: http://www.cs.cmu.edu/~mgormley/courses/10701-f16/

Related courses

• 10-702 Statistical Machine LearningCarnegie Mellon University · 2 recommenders
• Machine Learning (Andrew Ng)Coursera · 240 recommenders
• Practical Deep Learning for Codersfast.ai · 112 recommenders
• CS231n: Convolutional Neural Networks for Visual RecognitionStanford University · 39 recommenders
• Deep Learning Specialization (Andrew Ng)Coursera · 31 recommenders
• Neural Networks for Machine Learning (Geoffrey Hinton)Coursera · 25 recommenders
• CS229 Machine LearningStanford University · 20 recommenders
• Learning From DataCaltech · 20 recommenders