Khan Academy has excellent material covering Probability and Statistics (https://www.khanacademy.org/math/probability) and Linear Algebra (https://www.khanacademy.org/math/linear-algebra).

This is exactly where I'm learning from as well.

Would you mind sharing any of the resources you are using for re-learning? I've been meaning to do the same.

For probability/statistics you could also use the MIT Course https://www.edx.org/course/introduction-probability-science-...

Same course if you prefer the classroom lectures http://ocw.mit.edu/courses/electrical-engineering-and-comput...

Or if you want more rigor you can go through these notes that cover the same material but in a more formal way (via sigma algebras and measure theory) http://ocw.mit.edu/courses/electrical-engineering-and-comput...

Just saying, but if you want to hop onto the ML bandwagon (for instance), then don't bother going over linear algebra or probabilities first, and instead just learn what you need as you go. For example, the first sections of this book are already devoted to getting you on the right track, and it's somewhat standard to do so. And besides, there's no need in learning what are rotation matrices if you won't use them.

As a counterpoint, if parent is interested in taking ML further, a solid foundation in linear algebra will be huge when more advanced signal processing applications come up.

A couple of friends recommended these:- (Not sure if they are relevant though for deep learning specifically)

1) http://ocw.mit.edu/courses/mathematics/18-06-linear-algebra-... 2) https://www.khanacademy.org/math/linear-algebra/vectors_and_...

If anyone knows anything else (relevant to deep learning) could you please share :)

Introduction To Statistical Learning:

http://www-bcf.usc.edu/~gareth/ISL/

Is an excellent statistical learning reference.

I've been going through this series of video lectures on Youtube:

https://www.youtube.com/playlist?list=PL5102DFDC6790F3D0

for a basic "Stats 101" course.

There's also this archived Coursera course. There aren't any active sections to sign up for, but the videos are still available:

https://class.coursera.org/introstats-001

I'm mostly using Khan Academy at the moment. But I see several people already posted alternatives which is nice to have ;)

* Foundations of Machine Learning

* All of Statistics

* Doing Bayesian Data Analysis

Also the ML specialization on Coursera

There isn't much hard probability/statistics in deep learning since most of the stuff is empirical(IE: these neural network architectures work b/c we tried it and it works!). I'd say that deep learning is very accessible to the novice practictioner if you really want to dive into it; it doesn't require the same sort of mathematical background that something like signal processing might.

If you want to learn probability and statistics I recommend http://probabilitycourse.com

For linear algebra I heard Paul Dawkins' document is great, it's not on his site anymore but you can find it online. I've read calculus 1 and 1/3 of calculus 2 and it's good material.

This book looks amazing. Thanks for this.

I am a big fan of Linear Algebra Done Right, if you are looking for an actual, dead-tree book with good explanations.