Neural networks from scratch. Overview of courses and articles in Russian, free of charge and without registration

    On Habré periodically appear reviews of courses on machine learning. But such articles are more often bookmarked than the courses themselves. The reasons for this are different: courses in English, require a confident knowledge of matane or specific frameworks (or, on the contrary, the initial knowledge necessary to complete the course is not described), are on other sites and require registration, have a schedule, homework and are difficult to combine with workdays . All this prevents from now from scratch to begin to dive into the world of machine learning with its own speed, exactly to the level that is interesting and at the same time to skip uninteresting sections.

    In this review basically there are only links to articles on Habré, and links to other resources as an add-on (information on them in Russian and do not need to be registered). I read all the articles and materials I recommended personally. I tried each video course to choose what I like and help the others. Most of the articles I have read before, but there are also those that I stumbled upon while writing this review.

    The review consists of several sections, so that everyone can choose the level from which to start.
    For large sections and video courses, approximate time costs, necessary knowledge, expected results and tasks for self-examination are indicated.

    Most of the articles were not written in a single course, so information can be duplicated. If you see that you know some part of the article, then you can safely skip it, if you did not go broke with this information in the previous article, then you have a chance to read the same thing, but in other words, which should help the absorption of the material.

    Introductory articles

    Required level: school education, knowledge of Russian language.
    Required time: a few hours.

    It would seem that it is worth starting the study with the article Artificial Neural Network on Wikipedia, but I do not recommend it. The most descriptive description discourages all desire to study neural networks.

    Neyronki 5 minutes (too simplistic a description for the humanities, but it only takes 5 minutes)
    Artificial neural networks in simple terms (better to spend 15 minutes on this article)
    Fundamentals INS (one of the four articles of the Tutorial - Neural networks )
    Neural networks for beginners. Part 1 and Part 2
    Neural networks, fundamental principles of operation, diversity and topology
    Artificial neural networks and minicolumns of the real cortex (ninth part of the course The Logic of Consciousness )

    The task
    Прежде чем переходить к следующему уровню, создайте в онлайн конструкторе сеть. Посмотрите все 4 примера, и в последнем (спираль) обучите сеть за не более чем 100 эпох до уровня ошибки не более 0.1%, используя при этом минимальное количество нейронов и слоёв.

    Expand horizons

    Required level: basic understanding of the work of neural networks.
    Required time: a few hours.

    A short course of machine learning or how to create a neural network to solve the scoring problem.
    The most important thing about neural networks. Lecture in Yandex (I recommend to watch only video for 1 hour, read the article seemed rather hard)
    Introduction to neural network architectures
    What is a convolutional neural network
    Convolutionary neural network, part 1: structure, topology, activation functions and training set
    Zoo of neural network architectures. Part 1 and Part 2 (No special scrutiny, just look at the beautiful pictures and read the description diagonally)

    The task
    Перечислите основные:
    • типы задач, которые решают нейронные сети
    • типы архитектур нейронных сетей
    • функции активации
    • типы нейронов / слоёв

    We deepen knowledge

    Required level: understanding of the work of neural networks, knowledge of basic architectures.
    Required time: several tens of hours.

    A course on Deep Learning on fingers from AFTI NGU (14 videos, 15 hours, will be informative)
    OpenDataScience and Mail.Ru Group machine learning open course materials (10 videos, 20 hours, it will be difficult)
    Tekhnosfera Lectures. Neural networks in machine learning (14 videos, 25 hours, will be boring)

    To decide for myself and help with the choice of other habrovchanam, I built a schedule for the fall of interest in the course based on the fall in the number of views of each next video. The conclusions are disappointing - few people reach the end. The largest percentage of those that have come to the end is the course from AFTI NGU.

    (The graph of the fall in the number of views was drawn up a couple of months ago and the current picture may differ slightly).

    Examples of practical application

    This includes mostly only articles after which people who have read them will be able to reproduce the described results themselves (there are links to source codes or online services) of the

    TOP30 most impressive machine learning projects over the past year (v.2018)
    Image quality improvement using neural network
    Detection body parts using deep neural networks.
    Real-time classification of objects.
    We color a black and white photo using a neural network.
    Change sex and race on a selfie using neural networks
    How to distinguish between British and American literature using machine learning
    Splitting text into sentences using
    Tomit -parser WaveNet: a new model for generating human speech and music
    Analysis of the Quran using AI
    How many neurons do you need to know if the Alexander Nevsky Bridge is divorced?
    How many cats on Habré?
    Trade knows when you are expecting a child. The
    Stanford Neural Network determines the tonality of the text with an accuracy of 85%.
    Fuel for AI: a selection of open datasets for machine learning

    Other materials

    Articles and courses that are not included in my review, but you might like it.

    Neural networks in pictures, from one neuron to deep architectures (python, numpy)
    Basic principles of machine learning for example linear regression (python, numpy, mata)
    convolutional neural network, part 2: Learning algorithm backpropagation (mata)
    Neural network stepik .org (in the review two years ago, it was already called obsolete)
    Course on machine learning on Coursera from Yandex and HSE (the course is available only after registration, NumPy, Pandas, Scikit-Learn)
    Deep Learning For Coders (7 videos, 15 hours, English language)
    Course Deep Learning from Google at udacity(English)
    Course Structuring Machine Learning Projects on Coursera (paid, English)

    Other articles reviews on learning machine learning

    Where and how to study machine learning? (English)
    What to read about neural networks 10 books (English)
    We study independently: a selection of video courses on Computer Science (English)
    Review of courses on Deep Learning (English)
    10 courses on machine learning for the summer (English / Russian, for a fee / free)

    Reading these articles and pushed me to write my own, in which there would be materials only in Russian, without registration and the requirement of 5 years of matan.
    I hope that my article will have fewer comments like:
    “I threw it in the bookmarks. Of course, I will not watch them. ”

    I ask all interested parties to respond to polls after the article, well, subscribe to not miss my next articles, put likes to motivate me to write them and write questions in the comments (typos are better in a personal).

    Traditional warning: I do not respond to messages in a personal / social networks / telegram, etc. If you have a question, ask it in the comments.

    Only registered users can participate in the survey. Sign in , please.

    Indicate your level of theoretical knowledge about neural networks.

    Show your experience with neural networks in practice

    Courses that took place

    Courses that I take and recommend

    The reasons why I do not pass / did not take a course on neural networks

    Also popular now: