I don't know whether to take this course or the machine learning one. The both seem very interesting, but I only have time for one. I don't care much about robots, and was partly sold by Ng's separating music from background. OTOH I want to learn Bayes networks and natural language processing. I'd appreciate any advice.
My impressions: CS 221 (AI) is taken mostly by sophomores and juniors who are interested in AI, but come from all areas within CS. CS 229 (ML) is taken mostly by juniors and seniors who are on the AI track. CS 229 has a reputation for being the harder class. I get the idea that people come out of 221 with a knowledge of what techniques are out there so that they can accomplish simple tasks and know where to look when they need to learn more, and that people come out of 229 with a relatively firm foundation to solve ML problems (at least, as firm a foundation as you can get in 3 months in a large and difficult field).
for what it's worth, if you take the ML class, you will learn most of the things you would learn in the AI class and more - although it does get a bit rigorous, and will take more time than the AI class would. from personal experience, I feel like Ng's class gave me a more thorough foundation in the math behind the concepts, and was more challenging to boot - so I'd recommend it if you're feeling up for it.
I know that I hardly have time for one of them, but greedily want to try all three. I wonder if there is an expectation for the course to be available again, or at least provide the full materials afterwards. And if there is a penalty for failing/dropping out of them due to time constraints.
You can find some of the materials for last year's ML class at http://www.stanford.edu/class/cs229/.
CS 221 had a similar one, although it got taken down recently. I imagine you'd at the very least be able to access the materials while the class is ongoing or shortly thereafter for archival purposes.
