University of Warsaw - Central Authentication System

Deep neural networks

General data

Course ID:	1000-317bDNN
Erasmus code / ISCED:	11.3 The subject classification code consists of three to five digits, where the first three represent the classification of the discipline according to the Discipline code list applicable to the Socrates/Erasmus program, the fourth (usually 0) - possible further specification of discipline information, the fifth - the degree of subject determined based on the year of study for which the subject is intended. / (0612) Database and network design and administration The ISCED (International Standard Classification of Education) code has been designed by UNESCO.
Course title:	Deep neural networks
Name in Polish:	Głębokie sieci neuronowe
Organizational unit:	Faculty of Mathematics, Informatics, and Mechanics
Course groups:	(in Polish) Przedmioty obieralne na studiach drugiego stopnia na kierunku bioinformatyka Elective courses (facultative) for Computer Science Elective courses for Computer Science and Machine Learning Obligatory courses for 1st year Machine Learning Specific programme courses of 2nd stage Bioinformatics
ECTS credit allocation (and other scores):	6.00 Basic information on ECTS credits allocation principles: the annual hourly workload of the student’s work required to achieve the expected learning outcomes for a given stage is 1500-1800h, corresponding to 60 ECTS; the student’s weekly hourly workload is 45 h; 1 ECTS point corresponds to 25-30 hours of student work needed to achieve the assumed learning outcomes; weekly student workload necessary to achieve the assumed learning outcomes allows to obtain 1.5 ECTS; work required to pass the course, which has been assigned 3 ECTS, constitutes 10% of the semester student load. view allocation of credits
Language:	English
Type of course:	elective monographs
Prerequisites (description):	Proficiency in Python programming.
Short description:	The goal of the course is to show usage cases for deep neural networks. During the course state-of-the-art techniques, algorithms and tools will be presented. Among others two main blocks of the course will concern image classification and text processing.
Full description:	1. Introduction to neural networks: activation functions, loss function, back-propagation, optimizers, SGD, gradient flow, optimizing hyperparameters, regularization (dropout, batch normalization). 2. Hardware and software for deep learning 3. Convolutional neural networks: classification, detection, segmentation. 4. Generative modelling - VAE, GANs. 5. Recurrent neural networks. 6. Language modelling. 7. Transformers. 8. Reinforcement learning: DQN, policy gradients. 9. Applications (e.g., Alpha Go, ChatGPT).
Bibliography:	Online books: http://neuralnetworksanddeeplearning.com/ http://www.deeplearningbook.org/
Learning outcomes:	Knowledge: the student * has based in theory and well organized knowledge in the scope of machine learning, and in particular of problems related to neural networks learning algorithms as well as convolutional and recursive architecture [K_W08]. Abilities: the student is able to * use English at the proficiency level B2+ of Common European Framework of Reference for Languages, with particular emphasis on the computer science terminology [K_U02]; * make use of a chosen modern library of machine learning procedures [K_U12]; * implement image classification algorithms using convolutional neural networks and text transformation algorithms using recursive neural networks [K_U13]. Social competences: the student is ready to * critically evaluate acquired knowledge and information [K_K01]; * recognize the significance of knowledge in solving cognitive and practical problems and the importance of consulting experts when difficulties arise in finding a self-devised solution [K_K02]; * think and act in an entrepreneurial way [K_K03].
Assessment methods and assessment criteria:	Final grade is based upon the credit programming project, homeworks (computer programs) and exam in laboratory.

Classes in period "Winter semester 2024/25" (past)

Time span:	2024-10-01 - 2025-01-26	Selected timetable range: weekly course term Go to timetable MO LAB LAB LAB TU LAB LAB LAB W WYK LAB LAB LAB TH LAB LAB FR
Type of class:	Lab, 30 hours more information Lecture, 30 hours more information
Coordinators:	Marek Cygan, Marcin Mucha
Group instructors:	Kamil Ciebiera, Bartłomiej Cupiał, Marek Cygan, Mateusz Doliński, Marcin Mucha, Mateusz Olko, Aleksy Schubert, Konrad Staniszewski, Maciej Stefaniak, Marcin Wierzbiński, Przemysław Wiszniewski, Marcin Wrochna
Students list:	(inaccessible to you)
Credit:	Examination

Classes in period "Winter semester 2025/26" (future)

Time span:	2025-10-01 - 2026-01-25	Selected timetable range: weekly course term Go to timetable MO LAB LAB LAB LAB TU LAB LAB W WYK LAB LAB LAB LAB LAB LAB TH LAB LAB FR LAB LAB LAB
Type of class:	Lab, 45 hours more information Lecture, 30 hours more information
Coordinators:	Marek Cygan, Marcin Mucha
Group instructors:	Marek Cygan, Mateusz Doliński, Jowita Drozdowicz, Michał Krutul, Marcin Mucha, Stanisław Purgał, Aleksy Schubert, Maciej Stefaniak, Paulina Tomaszewska, Marcin Wierzbiński, Przemysław Wiszniewski, Maciej Wojtala, Marcin Wrochna
Students list:	(inaccessible to you)
Credit:	Examination

Course descriptions are protected by copyright.
Copyright by University of Warsaw.