How should I start with learning math required for AI [closed]

Question

I have studied mathematics, but that was long time ago. I have been a programmer for 8 years but when I started to study concepts in AI and data mining I find it very difficult to understand the theory.

Now I have wasted 2-3 years and I have got nothing. I need to first understand the math concepts required to learn AI and data mining.

I don't know where to start. Which books and tutorials do you recommend I should start with from the AI point of view.

How should I go about obtaining the fundamental requirements to use AI and Data Mining concepts.

EDIT: I got this list from internet

Matrix algebra: most machine learning models are represented as matrices and vectors. Concepts like eigenvectors and singular value decomposition appear all over the place.

Bayesian statistics: probability, Bayes' rule, common distributions (e.g., beta, Dirichlet, Gaussian), etc.

Multivariable calculus: most learning techniques use gradients and Hessians at their core to fit parameters. (If you want to get fancier, study numerical optimization.)

Information theory: entropy, KL divergence, etc. Just the basics here.

In limited cases, higher-level math can be useful. E.g., to understand manifold learning, you'll want to know some basic notions from geometry and topology. Occasionally abstract algebra is used (e.g., see "expectation semirings" for learning on hyper-graphs). I would learn these as-needed, but if you have a chance to learn them early it can't hurt.

Can anyone recommend some books on those

Answer 1

My resource for studying math : http://www.khanacademy.org/

You will be able to find A LOT on all math fields.

Answer 2

I agree with @Lostdreamer that KhanAcademy.org has great material for learning various math concepts.

For an excellent introductory online course on Machine Learning I highly recommend the Machine Learning course being offered on Coursera.org. It is taught by Stanford Professor Andrew Ng You can watch the videos as many times as you need to understand the concepts.

The exercises and programming assignments help drive home the concepts.

I recommend that you register for it the next time it is offered. Here's a link to the course registration page.

Here's a link to a preview of the material in the course.

The course contains a basic review of linear algebra including basic matrix concepts that help me review this material.

Answer 3

I highly recoment @HeatfanJohn 's course, I've already made it, without any knoledge of AI and it turned out pretty good, the teacher is amazing and the course is extremely clear, try it!

In addition I made this other AI course in the same time as the other. This one is much more general, you will learn a bit about everything in AI and there are not any previous knowledge you should have. If you are not used to do math, this one is easier than the ML one (in ML you need to make exercises in matlab, that are sometimes a little bit tricky) but I found it more interesting for a general overview. I highly recommend you to do both https://www.ai-class.com/

One you become addicted to AI (you will for sure if you make this two courses!) I reccomend Udacity, an amazing computer science free online "university". The best teacher in the world teaching you awesome things for free. If this is not awesome enough I'll tell you that the AI class teachers made this web page. One is Google's research director (Peter Norvig) and other one is the guy that made the first autonomous driving car (Sebastian Thrun). Awesome people