Take the 2-minute tour ×
Computer Science Stack Exchange is a question and answer site for students, researchers and practitioners of computer science. It's 100% free, no registration required.

http://www.scotthyoung.com/blog/mit-challenge/#1

This guy's work is mind blowing. He learned the 4 year MIT CS curriculum in 1 year, at home through opencourseware. I want to get into artificial neural networks and machine learning, and I thought doing some of the courses he did would help. Problem is, I have no idea which ones, and in what order! Some of the ones I think I should do are the single and multivariable calc, logic 1 and 2, artificial intelligence, mathematics for cs, etc.

Which ones should I do, and what order?

Thank you all!

share|improve this question
1  
It depends on your knowledge at the moment. You may need to learn also basic programming, data structures, algorithms, discrete mathematics, calculus, analytic geometry or even some math from school –  Anton Nov 19 '12 at 13:39
add comment

closed as too localized by A.Schulz, Gilles Nov 19 '12 at 14:53

This question is unlikely to help any future visitors; it is only relevant to a small geographic area, a specific moment in time, or an extraordinarily narrow situation that is not generally applicable to the worldwide audience of the internet. For help making this question more broadly applicable, visit the help center.If this question can be reworded to fit the rules in the help center, please edit the question.

1 Answer

Pattern Recognition and Machine Learning by Christopher M. Bishop is a good textbook. It covers much of the learning theory up to date, although I found this book hard to read it will give you a solid and fundamental understanding of learning theory.

Mathematical background: you will need to be familiar with linear algebra(properties about matrices etc), statistics(good understanding of probability theory and statistical inference is a must), calculus(multi-variable) and linear programming(optimizing objective functions, duality etc...)

Andrew Ng from Stanford offers an on-line course. The course is not difficult at all and there are programming assignments. I found that the course is geared toward programming(practical uses) rather than research(not theory oriented).

Many universities around the world offer these courses, so you will find much of the lecture notes on-line, usually reading lecture notes is easier to follow than the text.

Course Notes that cover optimization and linear programming: http://www.google.ca/url?sa=t&rct=j&q=combinatorics%20and%20optimization%20co250&source=web&cd=2&ved=0CCUQFjAB&url=http%3A%2F%2Fwww.math.uwaterloo.ca%2F~jochen%2Fdocs%2Fco250-notes.pdf&ei=a8ypUISLBcjgyQHlw4DACg&usg=AFQjCNGr0NTuoEVwHBBxejnAFr2xLHzYuw&cad=rja

Free textbook that covers probability and statistics: http://www.google.ca/url?sa=t&rct=j&q=statistical%20inference%20and%20probability%20theory%20pdf&source=web&cd=2&cad=rja&ved=0CCkQFjAB&url=http%3A%2F%2Ffaculty.ksu.edu.sa%2Fmahdy%2Fstat%2520cources%2FCambridge%2520University%2520Press%2520-%2520Probability%2520Theory%2520and%2520Statistical%2520Inference%2520842pg.pdf&ei=28upUILnD4aayQHE44G4Aw&usg=AFQjCNFPHvK-gMD2EhtODVsoITr5Q0v-iQ

Machine learning course notes: https://cs.uwaterloo.ca/~ppoupart/teaching/cs485-winter12/cs485-winter12.html

Machine Learning text: http://research.microsoft.com/en-us/um/people/cmbishop/prml/

share|improve this answer
add comment

Not the answer you're looking for? Browse other questions tagged or ask your own question.