Is this book a good intro to machine learning?

Take an actual course in ML and then that book with actually make sense, there's some good one's avail from CMU with lectures functionalcs.github.io/curriculum/#org0cfab06

All you need is a basic background in Linear Algebra though even that is self contained within most grad level ML intro courses. After one of those courses you can start reading articles out of the Journal of ML and have an idea of what's going on.

There's tensorflow library books on libgen, it uses python wrappers but it would help to have some statistics background to know what you're doing.

R is an open source re-implementation of the commercial S language by John Chambers. (There are some differences in scoping iirc). All of it's 'modern' PL constructs have already been used in Lisp dialects before, there's nothing really new there except R interprets character vectors of data frames as factor vectors by default, which will usually break something.

If anybody wants to know R you absolutely have to read 'Advanced R' or you won't understand what's going on when things break adv-r.had.co.nz/

R is an open source library built by and for statisticians, who are notoriously CS-impaired and incredibly autistic. Add the fact that it's also somehow used by academia's untermeschen known as economists, and you have the perfect storm of autism and incompetence.

Sure, it's not as bad as retard-tier abortions like Stata or Eviews, but stay THE FUCK away from R if you don't want to waste your time.

Python is a necessay evil as it's somehow intuitive to use it as the general framework for a complex API, and I had to set aside my prejudice against it.

t. TensorFlowfag

What would you recommend instead? It seems like if I'm going into the sciences and want to do any sort of calculations or statistics, I should probably stick to Python, C++, MATLAB, and then something like Maple.

I have known vector calculus for many years???

I own my own business???

Projecting much?

stick with python

>Pattern Recognition and Machine Learning by Christopher Bishop
>The Elements of Statistical Learning by Jerome H. Friedman, Robert Tibshirani, and Trevor Hastie
>Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville

These books are all pretty dense and will take a while to get through. But if you get through all of them you will pretty much be at PhD level in machine learning.

>>Pattern Recognition and Machine Learning by Christopher Bishop

highly recommended.

machine learning with [insert language]

is probably a meme book for non-academics.

I agree with this. You probably don't want to learn machine learning in terms of some language other but that of mathematics.

>Packt
no, god no

holy fucking shit why would you even think it is. Those books are shit, written by people who dont even know the subject, full of grammar and conceptual errors, and only covers random bits and pieces of the subject.

Don't waste your time with machine "learning"
It's just a meme and noone will talk about it anymore in a few years

t. buttblasted engineering student

Lol sure kid

It will get rolled into standard software engineering toolkits. Every CS bachelors degree holder will be machine learning competent.

The real shit in AI right now is basically at the border between computational neuroscience and ML. Just look at Deep Minds hiring track record to get a feel for what the real shit is

you sure tell em bud!

(oh poor soul :( )

Any book with a title like with is always bad. And dates very quickly.

Thanks great recommendations. I know two of these and have now ordered the third (deep learning).