Deep Learning
Informacje ogólne
Kod przedmiotu: | 23A1P1-S |
Kod Erasmus / ISCED: |
11.9
|
Nazwa przedmiotu: | Deep Learning |
Jednostka: | Szkoła Główna Handlowa w Warszawie |
Grupy: | |
Punkty ECTS i inne: |
3.00 (zmienne w czasie)
|
Język prowadzenia: | angielski |
Efekty uczenia się: |
Wiedza: Students will learn the theoretical foundations of deep learning. Students will learn the basic tools for building deep learning models Students will be introduced to different frameworks and other programming tools necessary to build a proper deep learning model. Students will be introduced to different, state-of-the-art architectures of deep neural networks. Umiejętności: Students will be able to build, verify, and evaluate deep neural networks. Students will be able to collect and prepare data for deep learning approaches. Students will be able to visualize and present the results of their work. Students will be able to build a proper environment and workflow for deep learning models. Kompetencje społeczne: Ability of presenting and communicating acquired results to high-level managerial stuff Acquire the ability of continued learning of methods related to deep learning. |
Zajęcia w cyklu "Preferencje - Semestr letni 2024/25" (jeszcze nie rozpoczęty)
Okres: | 2025-02-15 - 2025-09-30 |
Przejdź do planu
PN WT ŚR CZ PT |
Typ zajęć: |
Zajęcia prowadzącego
|
|
Koordynatorzy: | (brak danych) | |
Prowadzący grup: | Bartosz Pankratz | |
Lista studentów: | (nie masz dostępu) | |
Zaliczenie: |
Przedmiot -
Ocena
Zajęcia prowadzącego - Ocena |
Zajęcia w cyklu "Semestr letni 2024/25" (jeszcze nie rozpoczęty)
Okres: | 2025-02-15 - 2025-09-30 |
Przejdź do planu
PN WT ŚR CZ PT |
Typ zajęć: |
Laboratorium, 14 godzin
|
|
Koordynatorzy: | (brak danych) | |
Prowadzący grup: | (brak danych) | |
Lista studentów: | (nie masz dostępu) | |
Zaliczenie: |
Przedmiot -
Ocena
Laboratorium - Ocena |
|
Skrócony opis: |
During this course, students will learn selected deep learning methods and their applications. The course will start with an introduction to the theoretical foundations of deep learning. In the latter part of the lecture, students will learn different neural network architectures, including convolutional neural networks, generative models (variational autoencoders, generative adversarial networks and stable diffusion models), reccurent and recursive neural networks and language models. Each topic will be complemented with practical experiments in Julia programming languages. The course requires finishing the Statistical Learning Methods as a prerequisite. |
|
Pełny opis: |
The goal of the course is to provide the basic knowledge of deep learning methods. Students will learn both, theoretical foundations and practical applications of Deep Learning methods. The course requires finishing the Statistical Learning Methods as a prerequisite. The course is prepared in Julia programming language. |
|
Literatura: |
Literatura podstawowa: Goodfellow I., Bengio Y., Courville A. (2016), Deep Learning (http://www.deeplearningbook.org/) Roberts D. A., Yaida S., Hanin B. (2022), The Principles of Deep Learning Theory: An Effective Theory Approach to Understanding Neural Networks, Cambridge University Press (https://deeplearningtheory.com/) Calin O. (2020), Deep Learning Architectures: A Mathematical Approach, Springer. Literatura uzupełniająca: Weidman S. (2019), Deep Learning from Scratch, first edition. O'Reilly Media, Inc. Howard J., Gugger S. (2020), Deep Learning for Coders with Fastai and PyTorch: AI Applications Without a Ph,D first Edition (https://course.fast.ai/Resources/book.html) Boyd S., Vandenberghe L. (2018), Introduction to Applied Linear Algebra ? Vectors, Matrices, and Least Squares (http://vmls-book.stanford.edu/) Publikacje własne: Bogumił Kamiński, Tomasz Olczak, Bartosz Pankratz, Paweł Prałat , dr Francois Theberge, Properties and Performance of the ABCDe Random Graph Model with Community Structure, W: Big Data Research,2022 |
|
Uwagi: |
Kryteria oceniania: egzamin tradycyjny-pisemny: 50.00% egzamin testowy: 0.00% egzamin ustny: 0.00% referaty/eseje: 0.00% projekty: 50.00% studia przypadków: 0.00% prezentacje indywidualne lub grupowe: 0.00% |
Zajęcia w cyklu "Semestr zimowy 2024/25" (w trakcie)
Okres: | 2024-10-01 - 2025-02-14 |
Przejdź do planu
PN WT ŚR CZ PT |
Typ zajęć: |
Laboratorium, 14 godzin
|
|
Koordynatorzy: | (brak danych) | |
Prowadzący grup: | (brak danych) | |
Lista studentów: | (nie masz dostępu) | |
Zaliczenie: |
Przedmiot -
Ocena
Laboratorium - Ocena |
|
Skrócony opis: |
During this course, students will learn selected deep learning methods and their applications. The course will start with an introduction to the theoretical foundations of deep learning. In the latter part of the lecture, students will learn different neural network architectures, including convolutional neural networks, generative models (variational autoencoders, generative adversarial networks and stable diffusion models), reccurent and recursive neural networks and language models. Each topic will be complemented with practical experiments in Julia programming languages. The course requires finishing the Statistical Learning Methods as a prerequisite. |
|
Pełny opis: |
The goal of the course is to provide the basic knowledge of deep learning methods. Students will learn both, theoretical foundations and practical applications of Deep Learning methods. The course requires finishing the Statistical Learning Methods as a prerequisite. The course is prepared in Julia programming language. |
|
Literatura: |
Literatura podstawowa: Goodfellow I., Bengio Y., Courville A. (2016), Deep Learning (http://www.deeplearningbook.org/) Roberts D. A., Yaida S., Hanin B. (2022), The Principles of Deep Learning Theory: An Effective Theory Approach to Understanding Neural Networks, Cambridge University Press (https://deeplearningtheory.com/) Calin O. (2020), Deep Learning Architectures: A Mathematical Approach, Springer. Literatura uzupełniająca: Weidman S. (2019), Deep Learning from Scratch, first edition. O'Reilly Media, Inc. Howard J., Gugger S. (2020), Deep Learning for Coders with Fastai and PyTorch: AI Applications Without a Ph,D first Edition (https://course.fast.ai/Resources/book.html) Boyd S., Vandenberghe L. (2018), Introduction to Applied Linear Algebra ? Vectors, Matrices, and Least Squares (http://vmls-book.stanford.edu/) Publikacje własne: Bogumił Kamiński, Tomasz Olczak, Bartosz Pankratz, Paweł Prałat , dr Francois Theberge, Properties and Performance of the ABCDe Random Graph Model with Community Structure, W: Big Data Research,2022 |
|
Uwagi: |
Kryteria oceniania: egzamin tradycyjny-pisemny: 50.00% egzamin testowy: 0.00% egzamin ustny: 0.00% referaty/eseje: 0.00% projekty: 50.00% studia przypadków: 0.00% prezentacje indywidualne lub grupowe: 0.00% |
Właścicielem praw autorskich jest Szkoła Główna Handlowa w Warszawie.