Introduction to deep learning using TensorFlow
Full course in Russian can be found at this link .
The original English course is available here .
The release of new lectures is scheduled every 2-3 days.
Let's learn more about those who prepared this course for us and will conduct it.
')
Three persons:
First, who are developer advocates ? Judging by this article from Habr these are evangelicals. Who are the evangelists?
Studying machine learning we will encounter many new and different terms, for example, such terms as artificial intelligence , machine learning , neural networks and deep learning . What do these terms really mean and how do they relate to each other?
Below we analyze each of these terms and show their connection with each other.
Artificial Intelligence : a field of computer science that aims to achieve the development of human-like intelligence from a computer. There are many ways to achieve this goal, including machine learning and deep learning.
Machine learning : a set of related techniques for using which a computer is trained to perform a certain task, rather than directly programming the solution of a problem.
Neural networks : a machine learning construct (structure) inspired by neuron networks (nerve cells) in the biological brain. Neural networks are a fundamental part of deep learning and will be studied (affected) in this course.
Deep learning : machine learning sub-area using multilayer neural networks (multi-layer neural networks). Often the terms "machine learning" and "deep learning" are interchangeable.
Machine learning and deep learning also consist of many sub-areas, branches and unique techniques. One of the most significant and well-known examples is the separation of “ learning with a teacher ” and “ learning without a teacher ”.
In simple terms, in “learning with a teacher,” you know what you want to teach a computer, while “learning without a teacher” is similar to allowing a computer to determine for itself what can be learned. “ Teaching with a teacher ” is the most standard type of machine learning, and we will focus on it in this course.
Python - basic knowledge (cycles, conditional operators, lists, arithmetic operations, and some other basic structures).
If you wish, you can use the TensorFlow.js library in your favorite JavaScript language in the browser.
TensorFlow also allows you to work, through the "ports" connections, with languages ​​such as Swift, R and Julia. Python and JavaScript, at the moment, have the most complete support, therefore recommended.
To reduce the amount of software that will need to be installed on a local machine, throughout the course we will use the free Google service - Colab based on Jupyter .
... and standard call-to-action - subscribe, put a plus and share :)
YouTube: https://youtube.com/channel/ashmig
Telegram: https://t.me/ashmig
Vkontakte: https://vk.com/ashmig
What kind of English language courses in this direction should be taken to translate for public and pack into materials (text + video)? What format of practical tasks is the most appropriate in these areas - ready-made assemblies on GitHub or code snippets for later own knowledge of all parts?
Any feedback is welcome!
The original English course is available here .
The release of new lectures is scheduled every 2-3 days.
Who are these people?
Let's learn more about those who prepared this course for us and will conduct it.
')
Three persons:
- Magnus Hyttsten , Developer Advocate, Google
- Juan Delgado , Content Developer, Udacity
- Paige Bailey , Developer Advocate, Google
First, who are developer advocates ? Judging by this article from Habr these are evangelicals. Who are the evangelists?
IT evangelist is a specialist professionally engaged in the promotion of information technology.Interesting.
Studying machine learning we will encounter many new and different terms, for example, such terms as artificial intelligence , machine learning , neural networks and deep learning . What do these terms really mean and how do they relate to each other?
Below we analyze each of these terms and show their connection with each other.
Artificial Intelligence : a field of computer science that aims to achieve the development of human-like intelligence from a computer. There are many ways to achieve this goal, including machine learning and deep learning.
Machine learning : a set of related techniques for using which a computer is trained to perform a certain task, rather than directly programming the solution of a problem.
Neural networks : a machine learning construct (structure) inspired by neuron networks (nerve cells) in the biological brain. Neural networks are a fundamental part of deep learning and will be studied (affected) in this course.
Deep learning : machine learning sub-area using multilayer neural networks (multi-layer neural networks). Often the terms "machine learning" and "deep learning" are interchangeable.
Machine learning and deep learning also consist of many sub-areas, branches and unique techniques. One of the most significant and well-known examples is the separation of “ learning with a teacher ” and “ learning without a teacher ”.
In simple terms, in “learning with a teacher,” you know what you want to teach a computer, while “learning without a teacher” is similar to allowing a computer to determine for itself what can be learned. “ Teaching with a teacher ” is the most standard type of machine learning, and we will focus on it in this course.
What do we need from the tools?
Python - basic knowledge (cycles, conditional operators, lists, arithmetic operations, and some other basic structures).
If you wish, you can use the TensorFlow.js library in your favorite JavaScript language in the browser.
TensorFlow also allows you to work, through the "ports" connections, with languages ​​such as Swift, R and Julia. Python and JavaScript, at the moment, have the most complete support, therefore recommended.
CoLab: sandbox for our applications
To reduce the amount of software that will need to be installed on a local machine, throughout the course we will use the free Google service - Colab based on Jupyter .
... and standard call-to-action - subscribe, put a plus and share :)
Video version of the article
YouTube: https://youtube.com/channel/ashmig
Telegram: https://t.me/ashmig
Vkontakte: https://vk.com/ashmig
PS
What kind of English language courses in this direction should be taken to translate for public and pack into materials (text + video)? What format of practical tasks is the most appropriate in these areas - ready-made assemblies on GitHub or code snippets for later own knowledge of all parts?
Any feedback is welcome!
Source: https://habr.com/ru/post/453482/
All Articles