I'm actually taking the Applied Machine Learning class at Stanford, and I'll be honest - I'm a little disappointed that most of the content is delivered through video instead of lectures. I find it difficult to actually watch through the videos, mostly because there's no easy way for me to skim or jump around the content. I've actually ended up using the notes from the class I took last year (http://cs229.stanford.edu/materials.html) if I need to refresh my memory on the finer points.
Prof. Ng did remark that they decided to switch to videos because they saw dropping attendance rates in the past as students begin to utilize our remote learning solution later in the quarter (i.e. get lazy to go to class), but I wish that there was also a transcribed version of the videos that could be made available for people who prefer learning that way.
I can relay some of the things Prof. Ng said in the first meeting of the CS229A class:
229A is definitely meant to be much less mathematically rigorous - he said that he expects some people who don't feel like they're necessarily up to 229 to take 229A first to gain more familiarity with the material. From the people that actually showed up to the lecture, it was mostly CS people - although it's hard to say what the online enrollment is like. It is definitely meant to be useful to anyone who wants to be able to get machine learning algorithms to work, not necessarily understand their finer points.
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.
For what it's worth, most of the programming in the ML class when I took it last year was MATLAB based - since it mostly involved lots of linear algebra, and using MATLAB meant you got matrix operations for free. AI class, on the other hand, involved coding an increasingly more intelligent Pacman agent in Python as we learned new approaches to optimizing reward.
Having said that, taking ML definitely made my theory stronger - but this was mostly due to the amount of proofs in the class, and not so much the programming :)
I took the ML class in Autumn quarter and the AI class in Winter quarter of last year, there is definitely a lot of overlap - although to that extent, it might make it easier since you won't have two disjoint topic sets to study.
ML definitely goes into more mathematical rigor, while AI tends to cover a wide range of topics in enough depth to know when to apply them and how to interpret results.
I'm very into association football (both watching and playing), although I attribute that more to growing up in Europe as a boy more than anything else.
I also spent 4 years studying jujitsu (ended up taking a break because of school, but am hoping to be back into it once I graduate). I have found it to be a great way to stay in shape both physically and mentally, and was also lucky enough to find a great community of people to train with.
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.
having taken an AI class (using AIMA) at my undergrad college, I can't say that Norvig co-teaching the class made it all that different - probably the most interesting difference was being able to hear him (and Thrun) talk about real-world applications of the concepts we were covering, be it in Google products or Stanford research.
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.
or maybe give a math minor a chance! I ended up majoring in both Computer Science and Theoretical Mathematics in my undergraduate institution - and while I feel that Real Analysis did not directly help my programming skills, it's definitely made me a lot more comfortable with proofs and being able to make sense of things like approximation algorithms for NP-Complete problems. I also concur that it's improved my general thinking prowess, since at the end of the day, math is just reasoning about well defined systems, which definitely has many parallels to computer science.
This is completely off-topic, but did you mean to call it l'hospital as opposed to L'Hôpital? I remember even my calculus book had similar errors, and I always wondered if it was just because the two looked so similar (or if there was any more reasoning behind it). didn't mean to nitpick, your comment just triggered a repressed train of thought :)
In a way - I read Programming Interviews Exposed, and it definitely helped to brush up on implementation details, but Skiena offers more of a cookbook approach to tackling algorithmically hard problems. The second half is full of generalized problems, as well as the potential approaches to solving them using the concepts introduced earlier. While this might not be as used on an interview (since the problems may be a little too involved), I think it's definitely much more valuable for actually solving problems.
I read Skiena's book as preparation for interviews after having gone through a course using CLRS the year before, and I definitely feel like that is the best way to do it. I feel like reading Skiena got me back to mostly the same place I was last year after being waist-deep in CLRS, but I do feel that a more thorough examination of algorithms is needed to really grasp a lot of the nuances. it's perfect for dusting off the cobwebs though!
not at all - I took both the ML and AI course equivalents, and I think it's awesome more people can benefit from the great instruction I've been lucky enough to receive. I do agree that I also became more familiar with the material during office hours and other interactions with the course staff, and I think the classes are already designed well enough that making the resources like videos and assignments available will not put too much additional burden on the instructors.
this is easily one of the best classes i've been able to take - as i said in the other thread, i was surprised to enjoy a 3-hour midterm! i think it's awesome they're making this available to more people.
I would say that the AI class is a good overview for the field of AI - but Machine Learning is a good in-depth discussion of the machine learning approaches, which will generally also expose you to a lot of other related AI concepts.
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.
I ended up taking the Norvig AI class after this one and felt that a large majority of the material was also covered in the ML class, but usually more rigorously in the latter and as a means to more interesting stuff. If you feel like covering the material with a definite mathematical bent, I would recommend checking out this class.
I took this class as CS 229 at Stanford, and will attest that it's pretty damn awesome (easily one of the best classes I've been able to take). The course really provides a thorough exploration of a lot of the main techniques in machine learning, and Prof. Ng also presents it in a very engaging and understandable way. This was one of the few classes where I enjoyed my 3-hour long midterm!
as a potentially different use case, I use my tabs as a stack for reading things (where I push a link when I see it), and will then read through them all in a serial fashion, closing things I'm 'done' with. this generally leads to me having reference and 'to read' tabs open, in addition to things I like to have on hand (i.e. emails, workflowy, HN). this generally adds up to 15-20 tabs in my main window on average, going up to as much as 30-40.
Not very much - most of the lectures stood on their own as far as explaining the concepts, although the book was sometimes useful to consult with regard to the details of an algorithm, for example. Much of that information can be found elsewhere though, so I imagine that you could still get a lot out of this course without AIMA.
I took a version of this class (also taught by Norvig and Thrun) last year, and I definitely found it very enjoyable. I ended up taking it after CS 229 (which covers the mathematical underpinnings of machine learning with some rigor), so I unfortunately couldn't evaluate how good of an introductory course to AI it would be (having covered a lot of the concepts prior), but even still it was a class I enjoyed. Of particular interest was hearing the instructors draw parallels to their work (particularly with Google and the DARPA challenge), which made a lot of the theoretical concepts much more tangible and helped me recognize their practical applications.
this is also a very introductory course. i think it's great for whetting the appetite for further research into particular areas, but it definitely glosses over a lot of the mathematical foundations that a course like CS 229 (mentioned elsewhere) thoroughly explores. as such, i'm not sure if there's much a top grade in this course would even signify beyond some amount of commitment and interest in artificial intelligence.