Where and how to study machine learning?

Hello!

It is no secret to anyone that interest in machine learning and artificial intelligence is growing at best exponentially. In the meantime, my Yandex Disk has turned into a huge dump of paperpers , and the bookmarks in Google Chrome have turned into a list, the length of which tends to infinity every day. Thus, in order to simplify the life of yourself and you, I decided to structure the information and give a lot of links to interesting resources that I studied and which I recommend to study to you if you are only at the beginning of the path (I will constantly replenish the list).

I see the way for the development of a beginner like this:



Try to start small at first, if you don’t have a VIC specialty on forecasting methods behind your back for 6 years, you should not immediately download the archive of E. Sokolov’s or K. Vorontsov’s lectures, perhaps articles on Medium will be better for you. Also, difficulties may arise with the understanding of algorithms, if you are poorly oriented in probability theory, optimization theory and statistics, therefore I advise you to look at Ozon, the Moscow House of Books and stock up on lectures in mathematics. Further, having familiarized with the theory it will be easier to apply knowledge in solving problems. Next, I will give you a list of interesting resources that I myself once studied. I wish you success :)

Newbies:

Life hacking for a quick selection of models from the team Sklearn



Data Science Glossary (eng.)

Crash-Course on basic articles on deep learning at Medium

TensorFlow Tutorial

Python vs. R - Differences (English)

Open Course Science Open Course Science Lectures on Habré

Excellent ML CheatSheet (eng.)

Convolutionary neural network arithmetic from Theano team (Eng.)

Excellent video tutorials on data analysis and econometrics in the language of R

Naive Bayes classifier do it yourself with Habra

Good explanations of how ROC-AUC works.
www.youtube.com/watch?v=21Igj5Pr6u4
www.youtube.com/watch?v=vtYDyGGeQyo

Machine Learning Basics (eng.)

Continuing:

GitHub by Evgeny Sokolov with Machine Learning lectures at HSE

Open Data Science organization blog on Habré (recommended)

Selection and evaluation of models - the basics (Sebastian Raska, eng.)

Mathematical teaching methods for precedents (machine learning theory), K. Vorontsov (recommended)

Book on natural language toolkit (nltk, eng.)

Support Vector Machines in Practice (Eng.)

Keras.js - machine learning in the browser, you can touch the work of machine learning algorithms, helps when learning

Data Mining Algorithms Using R - an interactive book on learning machine learning on R

Advantages and disadvantages of AUC and accuracy

Neural networks for transferring style to a photo (English) (I recommend)

Transferring style with TensorFlow (English)

Ritchie Ng - a collection of machine learning resources (eng.)

Review of optimization methods by gradient descent in practice (Eng.)

Lectures on support vector machines from Utah University (Eng.)

Loss Functions for the Classification Problem