2025/2026
Neural Networks and Deep Learning
Type:
Mago-Lego
Delivered by:
Big Data and Information Retrieval School
Where:
Faculty of Computer Science
When:
2, 3 module
Open to:
students of one campus
Instructors:
Mark Blumenau
Language:
English
Contact hours:
48
Course Syllabus
Abstract
The course "Neural Networks and Deep Learning" is devoted to the study of neural network models and their application to solve applied problems. During the course, students will master the skills of deploying neural networks for image and text analysis, preparing and processing data for training, evaluating the quality of models, and diagnosing problems. Special attention is paid to practical aspects: students will learn how to demonstrate the work of neural networks to users without technical training. The course includes lectures and seminars covering a wide range of topics from the basics of gradient descent and activation functions to modern architectures such as convolutional and recurrent networks, as well as transformers and multimodal models. Assessment of knowledge is carried out through practical tasks, participation in competitions and an exam.