Answer the question

In order to leave comments, you need to log in

R

R

RoflanDaniil2017-11-07 21:11:59

Another question is how to get started in machine learning. How to start to understand whether I am interested in doing this or not?

I read a lot of answers to questions about how to start in ml, everywhere they advise to study mathematics, and they almost don’t say what to do next. Started course on coursera. Terribly boring. Starting with this course is the same as starting to learn PL from the standard. Mathematics is used where it could not be used, which slows down learning. Plus you have to watch the video. I don't know what could be worse than video learning.

Is there a quick excursion to ml with the fastest possible transition to deep neural networks and practice? Preferably in text form, but not a book in the usual sense. An analogue of the "Quick start" section in any documentation.

Answer the question

In order to leave comments, you need to log in

1 answer(s)

@RoflanDaniil

X

xdgadd, 2017-11-07 @RoflanDaniil

> math is used where it could not be used

Machine learning == math. Any model from a mashob is a function optimized by various methods (most often by gradient descent) (sorry for such a simplification). Without mathematics, the maximum is to blindly poke models from the Internet and tune hyperparameters.

> preferably in text form... "quick start"

MNIST in 5 minutes with Keras .

Similar questions

B

W

A

K

A

Didn't find what you were looking for?

Ask your questionAsk a Question

731 491 924 answers to any question