Studies > Architectures and technologies of deep learning (HPC)

Architectures and technologies of deep learning (HPC)

Type: Normative

Department: system design

Lectures

SemesterAmount of hoursLecturerGroup(s)
732Associate Professor Lyashkevych V. Y.

Laboratory works

SemesterAmount of hoursGroupTeacher(s)
732

Опис навчальної дисципліни

The curriculum in the discipline “Architectures and technologies of deep learning” determines the content and scope of knowledge necessary for a specialist in intelligent data processing technologies.

The discipline covers the problems of studying the modern state of deep learning technologies, the issue of formalization and data processing in systems functioning technologies, and the study of modern computer data processing software.

Within the scope of the academic discipline, students study the methods used to build complex neural network models and optimization algorithms for the purpose of solving tasks of classification, detection, segmentation, etc.

Recommended Literature

  1. Martin T. Hagan. Neural Network Design, 2013. – 1012 p. – [Електронний ресурс]. – Режим доступу: https://hagan.okstate.edu/NNDesign.pdf 
  2. Pytorch Tutorial. – [Електронний ресурс]. – Режим доступу: https://pytorch.org/tutorials/beginner/basics/intro.html 
  3. Aurélien Géron. Hands-On Machine Learning with Scikit-Learn and TensorFlow: O’Reilly, 2017. – 718 p.
  4. Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning: MIT Press, 2016. – [Електронний ресурс]. – Режим доступу: https://www.deeplearningbook.org/ 
  5. Mathematics concept required for Deep Learning. – [Електронний ресурс]. – Режим доступу:  https://www.geeksforgeeks.org/mathematics-concept-required-for-deep-learning/ 
  6. Mohri M., Rostamizadeh A., Talwalkar A. Foundations of Machine Learning. MIT Press, 2012. 
  7. Pytorch Tutorial. – [Електронний ресурс]. – Режим доступу: https://github.com/yunjey/pytorch-tutorial 
  8. Recurrent Neural Network. – [Електронний ресурс]. – Режим доступу: https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate/recurrent_neural_network/main.py#L39-L58
  9. Bidirectional Recurrent Neural Network. – [Електронний ресурс]. – Режим доступу: https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate/bidirectional_recurrent_neural_network/main.py#L39-L58
  10. Language Model (RNN-LM). – [Електронний ресурс]. – Режим доступу: https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate/language_model/main.py#L30-L50 
  11. Andreas C. Müller, Sarah Guido. Introduction to Machine Learning with Python. O’Reilly Media, Inc., 2016
  12. Russell, Stuart J. Artificial intelligence: a modern approach / Stuart J. Russell, Peter Norvig; contributing writers: Ernest Davis … [et al.]. – 3rd edition. – Upper Saddle River: Prentice Hall, 2010. – xviii, 1132 p. ill., tab., schem. 25 cm. – (Prentice Hall series in artificial intelligence) ISBN: 978-0-13-604259-4 0-13-604259-7.
  13. Goodfellow, I., Bengio, Y.,, Courville, A. (2016). Deep Learning. MIT Press. ISBN: 9780262035613
  14. Bishop, C. M. (2007). Pattern Recognition and Machine Learning (Information Science and Statistics). Springer. ISBN: 0387310738.
  15. Simon Haykin. Neural Networks and Learning Machines, Third Edition // New York: Prentice Hall, 2009. – 936 p.
  16. Andrej Karpathy blog http://karpathy.github.io/
  17. Sebastian Ruder blog. http://sebastianruder.com/optimizing-gradient-descent/
  18. https://www.datacamp.com/tutorial/pytorch-tutorial-building-a-simple-neural-network -from-scratch
  19. https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial2/Introdu ction_to_PyTorch.html
  20. Machine Learning in Computer Vision / N. Sebe, Ira Cohen, Ashutosh Garg, Thomas S. Huang// Springer, 2005. – 249 p. – [Електронний ресурс]. – Режим доступу:
    http://silverio.net.br/heitor/disciplinas/eeica/papers/Livros/[Sebe]%20-%20Machine%20Learning%20in%20Computer%20Vision.pdf  
  21. Prompt Engineering Guide. – [Електронний ресурс]. – Режим доступу: https://www.promptingguide.ai/ 
  22. All Things Generative AI. – [Електронний ресурс]. – Режим доступу:  https://generativeai.net/
  23. Generative artificial intelligence. – [Електронний ресурс]. – Режим доступу:  https://en.wikipedia.org/wiki/Generative_artificial_intelligence

Силабус:

Завантажити силабус