Deep Learning (11504)
Basic information | |||||||||
| Charles University | |||||||||
| Deep Learning | |||||||||
| admission procedure in progress | |||||||||
| Variant code (CID): | 11504 | ||||||||
| Orientation: | microcredentials | ||||||||
| Faculty: | Faculty of Mathematics and Physics | ||||||||
| full-time | |||||||||
| Presential | |||||||||
| English | |||||||||
| Deep Learning | |||||||||
| 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. |
|||||||||
| The course covers the following techniques and tasks: • Feedforward deep neural networks (basic architectures and activation functions; optimization algorithms) • Regularization of deep models (L2, dropout, label smoothing, batch normalization) • Convolutional neural networks (image classification, image segmentation, object detection, fine-tuning pre-trained models) • Recurrent neural networks (LSTM, GRU, seq2seq) • Transformer architecture • Natural language processing (distributed and contextualized word representations, BERT, morphological tagging, named entity recognition, lemmatization, machine translation) • Deep generative models (variational autoencoders, generative adversarial networks, diffusion models, image and speech generation) • Structured prediction (CTC and speech recognition, seq2seq) • Introduction to deep reinforcement learning |
|||||||||
| The applicants should have basic Python programming skills and basic knowledge of algebra (matrices and vectors) and calculus (what is a derivative). However, it is also possible to acquire this knowledge during the course through self-study. Previous knowledge of machine learning is not necessary. | |||||||||
| Knowledge: The student 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 student characterizes the frameworks and hardware accelerators for the implementation of deep neural networks. Skills: The student implements the above-mentioned basic architectures in a framework for an implementation of deep neural networks. The student is able to use a HW accelerator for training. The student understands a scientific paper from the field of deep learning. Competence: The student 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. |
|||||||||
| https://ufal.mff.cuni.cz/courses/npfl138 | |||||||||
|
|||||||||
Accreditation | |||||||||
| 11000 - Univerzita Karlova | |||||||||
| 249/24 | |||||||||
| 29.5.2024 | |||||||||
| 29.5.2034 | |||||||||
Further detailed information | |||||||||
| 8 | |||||||||
| 210 (total number of hours) | |||||||||
| délka kurzu je včetně očekávané domácí práce (to je přesně z žádosti o akreditaci; vychází pak 26.25 hodin práce na jeden kredit; tato hodnota musí být v rozsahu 25-30). Samotná přímá výuka činí necelých 50 šedesátiminutých hodin (65 vyučovacích hodin o délce 45 minut), zbytek je samostatná práce. | |||||||||
| 1 | |||||||||
| Software and applications development and analysis (0613) | |||||||||
| Marked assignment Written examination |
|||||||||
|
|||||||||
| 17.2.2025 | |||||||||
| 29.5.2034 | |||||||||
 |
|||||||||
 |
|||||||||
| Institutional Quality Assurance | |||||||||
| Ensured by CU’s IEB as a part of the internal quality assurance process | |||||||||
| Ensured by CU’s IEB as a part of the internal quality assurance process | |||||||||
Date and venue of the course | |||||||||
| 18.02.2025 | |||||||||
| 30.9.2025 | |||||||||
| samotné přednášky končí 22. května 2025, úkoly je možné vypracovávat do 30. června 2025, zkoušku je možné složit do konce akademického roku | |||||||||
| 2024/2025 | |||||||||
| summer semester | |||||||||
| Malostranské náměstí 25 , 118 00, Praha | |||||||||
| S5 / S3 / S9 (jsou dvě paralelní přednášky, dvě paralelní cvičení a nepovinná konzultace; vše je vždy z jedné z uvedených učeben) | |||||||||
Information for applicants | |||||||||
|
|||||||||
| 5000 Kč / course | |||||||||
| 03.02.2025 | |||||||||
| 09.03.2025 | |||||||||
| Bc. Magdaléna Kokešová | |||||||||
| magdalena.kokesova@matfyz.cuni.cz | |||||||||
| 95155 1630 | |||||||||
|
|||||||||
Enrolment information | |||||||||
|
|||||||||