The "Deep Learning Development" course aims to develop models and train software to analyze processes and perform actions that are as similar as possible to human brain activity.

It can be said that Deep Learning is a field closely related to Machine Learning, but differs from it in one main aspect. The primary goals and operation of Deep Learning are to analyze and process data, but it employs an algorithm called an artificial neural network. This algorithm is "inspired" by human brain activity and aims to draw conclusions and operate in a manner similar to human decision-making, while enhancing performance and the quality of conclusions.

The ability to process massive amounts of data and improve outcomes, all while considering creativity, emotions, understanding of meaning, and more, leads to a shift in the resulting image and conclusions obtained after using Deep Learning development.

In the study of Deep Learning, we will practically learn and practice the development of neural networks, and work extensively with Convolutional networks PyTorch, Dropout, BatchNorm, Restricted Boltzmann Machines (RBM), and more, in the field of artificial intelligence. The industry demand and average salary for Deep Learning professionals are high.

A wide range of tech companies alongside cutting-edge startups in the industry are searching for Artificial Intelligence developers who will lead developments that are expected to change the technological landscape in the near future.

Advancements and increased efficiency in fields such as healthcare, customer service, autonomous vehicles, finance, and more are industries that are investing heavily in AI and Deep Learning developments. Skilled developers can successfully integrate into these sectors and enjoy a stable career, enriched with various professional development opportunities.

Who is the Deep Learning course for?

College/university graduates interested in specializing in the development of artificial intelligence/AI systems.
Hardware/software/computer science engineers with no experience in this field who are interested in professional reorientation.
Individuals with relevant background and previous experience, including Python programming and working with Linux operating systems.

Course Prerequisites

Basic knowledge of the Python programming language is an advantage.

Tensorflow Course Description

The Deep Learning course includes:

Lectures with a strong emphasis on practical exercises.
Exercises accompanied by explanations, homework assignments, and solutions on the course website.
Course booklet.
Videos and presentations on the course website.
Lectures are held once a week in the evening hours.

Our study program integrates knowledge and extensive hands-on practice. The course lessons focus on practical knowledge and skills required for the field, and they are developed in collaboration with technology companies in the industry. The content is continuously updated based on projects in our development department.

Course Structure

Ch. 1

Introduction to Deep Learning

Ch. 2

Convolutional Networks

Ch. 3

Recurrent Neural Network

Ch. 4

Restricted Boltzmann Machines (RBM)

Ch. 5

Generative Adversarial Networks

Ch. 6

Deploying a Sentiment Analysis Model

Ch. 7

Deep Learning with Python and PyTorch

Ch. 8

Autoencoders

Meet your instructor:

Alex Shoihat

Head of Machine Learning

Alex holds a B.Sc. in Information Systems and an M.A. in Electrical and Electronic Engineering.

As a Machine Learning Engineer at Embedded Academy, Alex specializes in the field of artificial intelligence, applying over 13 years of experience in project development, management, and transitioning from development to production in various domains such as Linux Embedded.

Throughout his career, Alex developed his expertise working with the integration of Machine Learning and Deep Learning in the Computer Vision and Data Analysis field.