Annotation

The objective of this course is to provide a comprehensive introduction to deep neural networks, which have consistently demonstrated superior performance across diverse domains, notably in processing and generating images, text, and speech.

The course focuses both on theory spanning from the basics to the latest advances, as well as on practical implementations in Python and PyTorch (students implement and train deep neural networks performing image classification, image segmentation, object detection, part of speech tagging, lemmatization, speech recognition, reading comprehension, and image generation). Basic Python skills are required, but no previous knowledge of artificial neural networks is needed; basic machine learning understanding is advantageous.

Students work either individually or in small teams on weekly assignments, including competition tasks, where the goal is to obtain the highest performance in the class.

Location

Malostranské náměstí 25 , 118 00, Praha

Results of learning

Knowledge: The Graduate describes and explain the basic building blocks of deep neural networks (FFN, RNN, CNN, Transformer), basic architectures (processing and generation of images, text, speech), optimization algorithms (SGD, Adam) and regularization techniques (dropout, batch norm, …). The Graduate characterizes the frameworks and hardware accelerators for the implementation of deep neural networks.

Skills: The Graduate implements the above-mentioned basic architectures in a framework for an implementation of deep neural networks. The Graduate is able to use a HW accelerator for training. The Graduate understands a scientific paper from the field of deep learning.

Competence: The Graduate proposes a method to solve a new (previously unknown to them) problem from the field of image/text/speech processing, and implements and evaluates it themselves.

Contact for applicants

magdalena.kokesova@matfyz.cuni.cz