MIT's undergraduate introduction to artificial intelligence, taught by Patrick Winston, covering search, constraint satisfaction, rule-based systems, learning methods such as support vector machines, and related symbolic AI topics. The OpenCourseWare version includes full video lectures and course materials.

Commenters call Patrick Winston's lectures brilliant and say the course is worth doing in full, with one praising OCW's offering as still a great resource.

What commenters said (9)

1. Strongly recommendsddavis2019in “Patrick Winston of MIT CSAIL has died”

   Very sad, he was an amazing teacher. I love his MIT 6.034 lectures on youtube. One of the best is the SVM lecture: https://www.youtube.com/watch?v=_PwhiWxHK8o -- it's awesome how he gives the lecture to completion without any notes.

2. Recommendsf1shy2022in “Ask HN: In 2022, what is the proper way to get into machine/deep learning?”

   Read “AI a modern approach“ and do the MIT and Stanford courses that are available in Youtube. Then you can go deeper into the branches presented in the book and courses. The problem I’m seeing now, ist that everybody seems to think AI/ML is NN. Nothing further from truth!

3. Recommendschlopez21b2020in “Ask HN: What are the best advanced computer science courses online?”

   Check out "Artificial Intelligence" on MIT OpenCourseware:

   https://ocw.mit.edu/courses/electrical-engineering-and-compu...

   OpenCourseware was historically one of the first offerings of its kind. I remember using it almost 20 years ago, and it's still a great offering.

4. Recommendsproverbialbunny2020in “How to Speak (2018) [video]”

   Later, I took a much smaller grad class with Prof Winston that had maybe 15 people in it. We spent half the time reading and discussing great AI papers.

   Is by any chance this recorded anywhere? I loved his AI class (MIT 6.034). He was one of my favorite teachers too. (Though OCW on my end.)

5. RecommendsWiretrip2019in “The BS-Industrial Complex of Phony A.I.”

   There are tonnes of other approaches to machine learning that don't involve backprop! There are also other approaches to neural netwroks that don't use backprop (have a look at Numenta's stuff for example). I suggest you watch Pat Winston's brilliant MIT AI lectures to see how huge the range of techniques is.

6. RecommendsJamilD2017in “Patrick Winston Explains Deep Learning”

   Patrick Winston is a great lecturer -- and it's worth it to do the whole 6.034 course if you have the time. A lot of the topics he goes over are considered "out of style" now, but sometimes old-school AI algorithms find their use in new places [0]…

   [0] https://blog.openai.com/evolution-strategies/

7. RecommendsYadi2015in “Ask HN: What are some good online resources to learn electrical engineering?”

   This is an awesome EE course from MIT on AI:

   MIT Course: 6.034 AI: Undergraduate level

   http://ocw.mit.edu/courses/electrical-engineering-and-comput...

8. MentionsPennRobotics2021in “MIT OpenCourseWare”

   True, but incomplete.

   Filtering just EE/CS, there are 30 or 35 courses with full video lectures on ocw.mit.edu (which are all hosted on Youtube AFAIK). OLL seems to have four.

   Sometimes lectures are linked on a class website e.g. the modern Underactuated Robotics lectures: https://underactuated.mit.edu/

   If you're going down the rabbit hole, search "site:https://video.odl.mit.edu/collections/" or videolectures.net or archive.org, or you can search MIT's student pages for class assignments. Honestly, this is the only way to find substantial info on some entire fields e.g. Thermal-Fluids Engineering (2.005 and 2.006) ... or Course 2, in general.

   It helps to learn a specific school's curriculum (Stanford and Berkeley also have great resources) and target specific courses. You won't find lectures such as MIT's Inference course by looking on Youtube and OCW alone.

   [Not just replying to parent comment] If you plan to teach, sample some lectures by Patrick Winston, Anant Agarwal, Donald Sadoway, robert ghrist, and/or David Malan. The modern approach to engineering instruction seems to be 5 to 15 minute snippets posted online, but these five are among my favorite when it comes to full lectures.

9. Mentionsrkabir2007in “Ask YC: AI”

   my TA secretly recommended Norvig's book over Winston's, but we used Winston's "Artificial Intelligence"

   For more philosophy, read Minsky's books / papers, and the readings outlined here: http://ocw.mit.edu/OcwWeb/Electrical-Engineering-and-Compute...

   Minsky's paper "Steps toward Artificial Intelligence" reads like a summary of 6.034 at MIT.

   Speaking of which: http://ocw.mit.edu/OcwWeb/Electrical-Engineering-and-Compute...

Related courses

• CS50: Introduction to Computer ScienceHarvard University · 72 recommenders
• Underactuated RoboticsMIT OpenCourseWare · 4 recommenders
• CS221: Artificial Intelligence: Principles and TechniquesStanford 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