Hello fellow /sci/, where I can find good reading material to

Bump I wanna know too. My uni doesn't have a course about neural networks yet and I want to go beyond simple character recognition/playing with google's examples

I also want to know. I'd prefer books over videos, since I can never focus.

File: plot_lasso_coordinate_descent_path_1.png (82KB, 800x600px) Image search: [Google]

82KB, 800x600px

I enjoyed this one -

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

people recommend andrew ng's course willy-nilly

My school's master's-level machine learning course recommended lots of additional readings from Machine Learning by Tom Mitchell. Out of the readings that I actually read (2 or 3 desu), I found them all pretty straightforward to follow. It was written in 97 but it's still really good for an introduction.

http://www.cs.cmu.edu/afs/cs.cmu.edu/user/mitchell/ftp/mlbook.html

There are lots of blog posts and such on specific stuff that are pretty solid, like this one:
http://colah.github.io/posts/2014-03-NN-Manifolds-Topology/

>>8578395
I didn't. It was pretty dry. It was more about statistics than machine learning.

>>8578437

They have Andrew Ng's machine learning lectures from Stanford on Youtube. I liked those a lot more than the "That's a little too rigorous. So, let's not do that" attitude of his MOOC.

>>8578441
Machine learning is statistics. If you want to learn machine learning you had better learn statistics. Statistics is not boring.

File: 1463670591206.jpg (42KB, 800x587px) Image search: [Google]

42KB, 800x587px

>>8578441
>it was more about statistics than machine learning
You don't know what machine learning is, do you?

http://yerevann.com/a-guide-to-deep-learning/

Yes I know you said "machine learning" and not "Deep learning" but we all know what you meant.

>>8578470
Statistics and numerical linear algebra