Deep learning models (am)
Type: For the student's choice
Department: computational mathematics
Curriculum
Semester | Credits | Reporting |
9 | 6 | Setoff |
Lectures
Semester | Amount of hours | Lecturer | Group(s) |
9 | 32 | Associate Professor Yu. A. Muzychuk | PMp-51m |
Laboratory works
Semester | Amount of hours | Group | Teacher(s) |
9 | 32 | PMp-51m | Associate Professor Yu. A. Muzychuk, Ya. S. Harasym |
Course description
The course “Deep learning models” is a continuation of the discipline Fundamentals of machine learning (AM). Its main goal is to acquaint the student with modern machine learning problems and popular methods of solving them – deep neural networks. The course covers the following sections: Fundamentals of Machine Learning, Convolutional Neural Networks for Computer Vision Problems, and Modeling Sequences in Recurrent Neural Networks. When considering these topics, the main focus is on establishing the necessary mathematical apparatus for solving the tasks, researching the architectures of the corresponding neural networks, and using modern libraries and tools for programming these algorithms. The presentation of the material is carried out using current terms and concepts from the field of information technologies.
Recommended Literature
- Géron A. Hands-On Machine Learning with Scikit-Learn and TensorFlow: Techniques and Tools to Build Learning Machines / Aurélien Géron. – O’Reilly Media, 2018. – 566p.
- Goodfellow I. Deep Learning / Ian Goodfellow, Yoshua Bengio, Aaron Courville. – MIT Press, 2016. – WWW: http://www.deeplearningbook.org
- Howard J. Deep Learning for coders with Fastai and PyTorch: AI applications without a PhD / Jeremy Howard, Sylvain Gugger. – O’Reilly Media, 2020. – WWW: https://github.com/fastai/fastbook
- McLure N. TensorFlow Machine Learning / Nick McLure. – Packt Publishing, 2017. – 351p.
- Zhang A. Dive into Deep Learning / A.Zhang, Zachary C. Lipton, Mu Li, Alexander J. Smola. – arXiv preprint arXiv:2106.11342, 2021. – WWW: https://arxiv.org/abs/2106.11342