Deep learning with neuralk networks Field of study: Computer Science
Programme code: W4-S2IN19.2022

Module name: Deep learning with neuralk networks
Module code: W4-IN-S2-20-F-UGzSN
Programme code: W4-S2IN19.2022
Semester:
  • summer semester 2025/2026
  • winter semester 2025/2026
  • summer semester 2024/2025
  • winter semester 2024/2025
  • summer semester 2023/2024
  • winter semester 2023/2024
Language of instruction: Polish
Form of verification: course work
ECTS credits: 4
Description:
At present, deep learning algorithms are increasingly used in modern information technologies. In 2012, a deep neural network dominated the prestigious competition dedicated to the automatic recognition of image content. Since then, neural networks have revolutionized methods of machine image analysis. Currently, neural networks are also the main engine of speech recognition algorithms and automatic text translation.
Prerequisites:
(no information given)
Key reading:
1. Tom Mitchell, Machine Learning, McGraw Hill, 1997. 2. Christopher M. Bishop Pattern Recognition and Machine Learning, Springer, 2007. 3. Paweł Cichosz, Learning Systems, WNT, 2000. 4. S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd Ed., Pearson, 2010. 5. D. Poole, A. Mackworth, Artificial Intelligence: Foundations of Computational * Agents, Cambridge University Press, 2010. Weka toolkit, http://www.cs.waikato.ac.nz/ml/weka/. 6. Machine learning with Scikit-Learn and TensorFlow, Aurélien Géron, Helion, 2018. 7. Python: machine learning / Sebastian Raschka, Vahid Mirjalili ; translation: Krzysztof Sawka, Helion, 2019.
Learning outcome of the module Codes of the learning outcomes of the programme to which the learning outcome of the module is related [level of competence: scale 1-5]
Has knowledge of artificial neural networks. [M_001]
 K_W09 [1/5]
Knows methods and algorithms for learning deep neural networks [M_002]
 K_W02 [1/5]
Is able to design and implement a deep neural network [M_003]
 K_U01 [1/5]
Can train a neural network to solve a specific machine learning problem. [M_004]
 K_U02 [1/5]
Can assess the effectiveness of a trained neural network. [M_005]
 K_U05 [1/5]
He knows the possibilities of modern neural networks. He is aware of the importance of machine learning methods in developing modern IT solutions. [M_006]
 K_K01 [1/5]
Type Description Codes of the learning outcomes of the module to which assessment is related
Colloquium [W_001]
Solving tasks and answering open questions.
 M_001 M_002
Implementation project [W_002]
Project evaluation after the multimedia presentation of the whole group.
 M_003 M_004 M_005
Multimedia presentation [W_003]
Assessment of the validity of the self-assessment of collective work and verification of the hypotheses.
 M_006
Form of teaching Student's own work Assessment of the learning outcomes
Type Description (including teaching methods) Number of hours Description Number of hours
lecture [Z_001]
Giving the educational content in verbal form with the use of content visualization. Focusing on conceptually difficult material and indicating addresses of websites and e-learning package
 15
Getting to know the topic of the lecture using the existing packages of methods: script, websites and e-learning package
 30 Colloquium [W_001]
laboratory classes [Z_002]
Detailed preparation of students for the implementation of algorithms with indication of the methodology of conduct, indication of the sequence of activities to be performed
 30
Self-development and preparation of students for the colloquiums of the laboratory. Project execution - implementation of a given system in a group of many people
 45 Colloquium [W_001] Implementation project [W_002] Multimedia presentation [W_003]
Attachments
Module description (PDF)
Information concerning module syllabuses might be changed during studies.
Syllabuses (USOSweb)
Semester Module Language of instruction
(no information given)