460-4140/01 – Deep Learning (HU)

Gurantor departmentDepartment of Computer ScienceCredits4
Subject guarantorprof. Ing. Jan Platoš, Ph.D.Subject version guarantorprof. Ing. Jan Platoš, Ph.D.
Study levelundergraduate or graduateRequirementChoice-compulsory type A
Year1Semestersummer
Study languageCzech
Year of introduction2022/2023Year of cancellation
Intended for the facultiesFEIIntended for study typesFollow-up Master
Instruction secured by
LoginNameTuitorTeacher giving lectures
PLA06 prof. Ing. Jan Platoš, Ph.D.
SVO0175 Ing. Radek Svoboda
Extent of instruction for forms of study
Form of studyWay of compl.Extent
Full-time Graded credit 2+2
Part-time Graded credit 18+0

Subject aims expressed by acquired skills and competences

The course aims to acquaint students with deep learning methods, deep neural networks, and other methods of advanced data processing. Students will be acquainted with basic and advanced deep learning methods and their applications over vector, image, text, and other data.

Teaching methods

Lectures
Tutorials

Summary

In the course, students will get acquainted with deep learning methods with particular emphasis on deep neural networks. Students build on their knowledge of machine learning and deepen it through demonstrations and a deep learning approach to various data types, from vectors, images, text, or data streams. Students will have the chance to test their knowledge and skills using appropriate tools and libraries over artificial and real data and interpret the results for their complete understanding.

Compulsory literature:

- Slides from Lectures [1] GOODFELLOW, Ian, Yoshua BENGIO a Aaron COURVILLE. Deep learning. Illustrated edition. Cambridge, MA: MIT press, 2016. Adaptive computation and machine learning series. ISBN 978-0262035613. [2] SAITOH, Koki. Deep Learning from the Basics: Python and Deep Learning: Theory and Implementation. Birmingham, UK: Packt Publishing, 2021. ISBN 978-1800206137. [3] GÉRON, Aurélien. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: concepts, tools, and techniques to build intelligent systems. Second edition. Beijing: O'Reilly, 2019. ISBN 978-1-4920-3264-9. [4] HOWARD, Jeremy a Sylvain GUGGER. Deep learning for coders with Fastai and PyTorch: Ai applications without a PhD. Sebastopol, CA: O´Reilly, 2020. ISBN 978-1-492-04552-6. [5] KELLEHER, John D. Deep learning. Illustrated edition. Cambridge: The MIT Press, 2019. MIT Press essential knowledge series. ISBN 978-0262537551. [6] KROHN, Jon, Grant BEYLEVELD a Aglaé BASSENS. Deep learning illustrated: a visual, interactive guide to artificial intelligence. Boston: Addison-Wesley, [2020]. ISBN 978-0135116692.

Recommended literature:

[1] AGGARWAL, Charu C. Data mining: the textbook. New York, NY: Springer Science+Business Media, 2015. ISBN 978-3-319-14141-1. [2] BRAMER, M. A. Principles of data mining. London: Springer, 2007. ISBN 1-84628-765-0. [3] LESKOVEC, Jure, Anand RAJARAMAN a Jeffrey D. ULLMAN. Mining of massive datasets, Standford University. Second edition. Cambridge: Cambridge University Press, 2014. ISBN 9781107077232. [4] WITTEN, Ian H., Eibe FRANK, Mark A. HALL a Christopher J. PAL. Data mining: Practical machine learning tools and techniques. Fourth Edition. Amsterdam: Elsevier, [2017]. ISBN 978-0-12-804291-5. [5] ZAKI, Mohammed J. a Wagner MEIRA JR. Data Mining and Analysis: Fundamental Concepts and Algorithms. 2nd edition. Cambridge, GB: Cambridge University Press, 2020. ISBN 978-0521766333. [6] LAPAN, Maxim. Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more. 1. Birmingham, UK: Packt Publishing, 2018. ISBN 978-1788839303.

Way of continuous check of knowledge in the course of semester

The student knowledge is checked during lab using exercises, home works and implementation of selected algorithm.

E-learning

Other requirements

Additional requirements are not placed on the student.

Prerequisities

Subject codeAbbreviationTitleRequirement
460-4139 SU Machine Learning Recommended

Co-requisities

Subject has no co-requisities.

Subject syllabus:

Lectures (topics): 1. Neural networks, principles, basic properties. 2. Neural networks - parameters. 3. Convolutional neural networks. 4. Autocoder. 5. Variation car encoder. 6. Recurrent neural networks. 7. Analysis of time series using neural networks. 8. Text classification - word representation 9. Language modeling using RNN 10. Vector data processing - Exploratory analysis and classification 11. Locating and recognizing objects in the image 12. Generative methods - GAN Exercises in the computer room: 1. Neural networks, principles, basic properties. 2. Neural networks - parameters. 3. Convolutional neural networks. 4. Autocoder. 5. Variation car encoder. 6. Recurrent neural networks. 7. Analysis of time series using neural networks. 8. Text classification - word representation 9. Language modeling using RNN 10. Vector data processing - Exploratory analysis and classification 11. Locating and recognizing objects in the image 12. Generative methods - GAN

Conditions for subject completion

Full-time form (validity from: 2022/2023 Winter semester, validity until: 2022/2023 Summer semester)
Task nameType of taskMax. number of points
(act. for subtasks)
Min. number of pointsMax. počet pokusů
Graded credit Graded credit 100  51 3
Mandatory attendence participation: The student is obliged to complete the assignment at the seminars and submit the project assigned by the instructor.

Show history

Conditions for subject completion and attendance at the exercises within ISP: Completion of all mandatory tasks within individually agreed deadlines.

Show history

Occurrence in study plans

Academic yearProgrammeBranch/spec.Spec.ZaměřeníFormStudy language Tut. centreYearWSType of duty
2024/2025 (N0612A140004) Information and Communication Security P Czech Ostrava 1 Optional study plan
2024/2025 (N0613A140034) Computer Science AZD P Czech Ostrava 1 Choice-compulsory type A study plan
2024/2025 (N0613A140034) Computer Science AZD K Czech Ostrava 1 Choice-compulsory type A study plan
2024/2025 (N0688A140014) Industry 4.0 AZD P Czech Ostrava 1 Compulsory study plan
2024/2025 (N2647) Information and Communication Technology (2612T025) Computer Science and Technology P Czech Ostrava 2 Choice-compulsory study plan
2024/2025 (N2647) Information and Communication Technology (2612T025) Computer Science and Technology K Czech Ostrava 2 Choice-compulsory study plan
2023/2024 (N0612A140004) Information and Communication Security P Czech Ostrava 1 Optional study plan
2023/2024 (N0688A140014) Industry 4.0 AZD P Czech Ostrava 1 Compulsory study plan
2023/2024 (N0613A140034) Computer Science AZD K Czech Ostrava 1 Choice-compulsory type A study plan
2023/2024 (N0613A140034) Computer Science AZD P Czech Ostrava 1 Choice-compulsory type A study plan
2023/2024 (N2647) Information and Communication Technology (2612T025) Computer Science and Technology P Czech Ostrava 2 Choice-compulsory study plan
2023/2024 (N2647) Information and Communication Technology (2612T025) Computer Science and Technology K Czech Ostrava 2 Choice-compulsory study plan
2022/2023 (N0613A140034) Computer Science AZD K Czech Ostrava 1 Choice-compulsory type A study plan
2022/2023 (N0613A140034) Computer Science AZD P Czech Ostrava 1 Choice-compulsory type A study plan
2022/2023 (N0688A140014) Industry 4.0 AZD P Czech Ostrava 1 Compulsory study plan
2022/2023 (N0612A140004) Information and Communication Security P Czech Ostrava 1 Optional study plan
2022/2023 (N2647) Information and Communication Technology (2612T025) Computer Science and Technology P Czech Ostrava 2 Choice-compulsory study plan
2022/2023 (N2647) Information and Communication Technology (2612T025) Computer Science and Technology K Czech Ostrava 2 Choice-compulsory study plan

Occurrence in special blocks

Block nameAcademic yearForm of studyStudy language YearWSType of blockBlock owner

Assessment of instruction



2022/2023 Summer