Stanford AI Classes
- Thread starter cardine
- Start date
When I was cleaning out my storage room the other day I found some of my old tests and quizzes from college...Nope don't feel like going through that daily kick in the nuts again anytime soon, not even an introductory class.
Ya'll have fun and let us know how it goes please.
Ya'll have fun and let us know how it goes please.
Cool links. Will definitely sign up when I have more time.
For now, I've been reading through [ame="http://www.amazon.com/gp/product/B0028N4WM4/ref=kinw_myk_ro_title"]Programming Collective Intelligence on my Kindle[/ame].
For now, I've been reading through [ame="http://www.amazon.com/gp/product/B0028N4WM4/ref=kinw_myk_ro_title"]Programming Collective Intelligence on my Kindle[/ame].
Anyone got any idea if you need a programming background to do something like this? I'm trying to learn more languages, but atm I can only code html/css & a little bit of javascript.
The syllabus mentions game AI, and practical applications - so some programming knowledge would be required/a plus. It also says that the course (being a 200 level) is aimed at advanced undergraduate - low-level graduate students. Those students have typically had at least 2-3 programming courses.
I suggest you give the video tutorials at TheNewBoston – Free Educational Video Tutorials on Computer Programming and More! a viewing. They are each between 5-10 minutes long, so you can get a good understanding relatively easily and apply it.
As an aside to the AI & ML courses the "Introduction to Databases" class is very basic and should be no trouble grasping if so inclined. You may be well past that skill level but if not it goes nicely with what we do.
From the overview of the AI course:
"Programming is not required, however we believe it will be very helpful for some of the homework assignments. You may write code in any language you would like to (we recommend Python if you are new to programming) and your code will not be graded. For example, a question might ask for 6 answers to the same problem but with varied inputs or parameters. You are welcome to work each one out by hand, however writing a program might be both faster and give you a better understanding of how the algorithm works."
That being said, it's kind of hard to wrap your head around some of the basic CSC concepts without playing around with them to see how they work (for me, at least). They recommend Python if you're new but I'd also recommend checking out Ruby. If you have a Mac you've already got Ruby installed.
We used this book in my first intro to CSC class The Pragmatic Bookshelf | Learn to Program and I found it pretty easy to follow, and I had never done any programming before. THat book uses Ruby.
I've purchased a few books from the Pragmatic bookshelf and I've found them all to be pretty good. Definitely go for the ebook option so you can always download updated versions if they update them.
All that being said, I've never really used Python before so I might try to do some of the homework using Python but I'll most likely be doing the majority using Ruby, if anybody wants to talk about the homework etc. Of course, after the answers are given, in agreement with the terms of the class.
There are two versions of the class "Basic", where you just answer questions to show you understood the lecture, and "Advanced" where you also have to do programming assignments. I think it's pretty programming-light compared to most other compsci classes... it's been designed to be accessible.
I'll be taking the ML course all the way through.
I'm in AI, but not at Stanford. It's like what was described above- you don't need to know programming, but the reason they say it helps is because if you've had programming courses, you are going to know data structures and have some exposure to logical thinking.
What is most helpful is if you understand graph theory, search trees, and the common algorithms associated with them. Like what is the most efficient way to search an extremely large structure, or what is the optimal path from node a to node b in a graph. AI will give some variations on the common algorithms that are fit to specific problems.
Also, we did some programming in LISP, though I don't know if Stanford's course does that.
What is most helpful is if you understand graph theory, search trees, and the common algorithms associated with them. Like what is the most efficient way to search an extremely large structure, or what is the optimal path from node a to node b in a graph. AI will give some variations on the common algorithms that are fit to specific problems.
Also, we did some programming in LISP, though I don't know if Stanford's course does that.
the stanford class goes over the Octave language, so they expect people to be using MatLab quite a bit with it.
What a pile of shit. I watched a few preview videos and it's all garbage theory.
h(x)=y
ok who cares.
Obviously if I feed information through a processor that is gives me my answer, I will get my answer.
h(x)=y
ok who cares.
Obviously if I feed information through a processor that is gives me my answer, I will get my answer.
Thanks for sharing the links bro! Awesomeness.. Now as someone who has got basic coding skills, do any of you guys recommend a particular coding language before doing this course?
I have made it my goal to within the next 12 months get good at a coding language, so maybe I can hit 2 birds with one stone if the coding language I should learn also applies to this course?
I have made it my goal to within the next 12 months get good at a coding language, so maybe I can hit 2 birds with one stone if the coding language I should learn also applies to this course?
Or maybe Java (Android) or ObjectiveC (iOS) if you plan on doing mobile development instead of web.
Either way, the techniques you learn from one language will usually be useful in other languages. Loops, variables, conditionals, iteration... they're all pretty universal. Once you learn one, it's easier to learn others.
The class will use Octave, but as Supergeek said, once you learn one language it is relatively easy to learn others as well.
Same here, I'll be looking to bring on someone soon for ML.