Artificial neural networks

General data

Course ID:	1100-3BN22
Erasmus code / ISCED:	11.303 Kod klasyfikacyjny przedmiotu składa się z trzech do pięciu cyfr, przy czym trzy pierwsze oznaczają klasyfikację dziedziny wg. Listy kodów dziedzin obowiązującej w programie Socrates/Erasmus, czwarta (dotąd na ogół 0) – ewentualne uszczegółowienie informacji o dyscyplinie, piąta – stopień zaawansowania przedmiotu ustalony na podstawie roku studiów, dla którego przedmiot jest przeznaczony. / (0612) Database and network design and administration The ISCED (International Standard Classification of Education) code has been designed by UNESCO.
Course title:	Artificial neural networks
Name in Polish:	Uczenie maszynowe i sztuczne sieci neuronowe
Organizational unit:	Faculty of Physics
Course groups:
Course homepage:	https://brain.fuw.edu.pl/edu/STAT:Uczenie_maszynowe_i_sztuczne_sieci_neuronowe
ECTS credit allocation (and other scores):	(not available) Basic information on ECTS credits allocation principles: the annual hourly workload of the student’s work required to achieve the expected learning outcomes for a given stage is 1500-1800h, corresponding to 60 ECTS; the student’s weekly hourly workload is 45 h; 1 ECTS point corresponds to 25-30 hours of student work needed to achieve the assumed learning outcomes; weekly student workload necessary to achieve the assumed learning outcomes allows to obtain 1.5 ECTS; work required to pass the course, which has been assigned 3 ECTS, constitutes 10% of the semester student load. view allocation of credits
Language:	Polish
Prerequisites (description):	Student should know the basic concepts in algebra and calculus. Student should know be able to program in python.
Mode:	Classroom
Short description:	Lecture and hands-on course introducing the concepts of modeling artificial neural networks and machine learning. Students will learn the theoretical basis and practical application to problem solving.
Full description:	Sylabus: 1. Linear regression 2. Linear neural networks 3. Perceptron 4. Backpropagation algorithm 5. Classification and logistic regression 6. Generative algorithms 7. Support Vector Machines 8. Unsuppervised learning 9. Reinforced learning. Theoretical concepts presented during lectures will be illustrated with practical examples in python during the hands-on classes.
Bibliography:	1. R. Tadeusiewicz, Sieci neuronowe. 2. Timothy Masters, Sieci neuronowe w praktyce Programowanie w języku C++. 3. J.Hertz, A. Krogh, R. Palmer, Wstęp do teorii obliczeń neuronowych. 4. S. Osowski, Sieci neuronowe w ujęciu algorytmicznym. 5. Z. Świątnicki R. Wantoch-Rekowski, Sieci neuronowe w zastosowaniach wojskowych. 6. J. Korbicz, A. Obuchowicz, D. Uciński, Sztuczne sieci neuronowe - podstawy i zastosowania. 7. D. Rutkowska, M. Piliński, L. Rytkowski, Sieci neuronowe, algorytmy genetyczne i systemy rozmyte. 8. J. Chromiec, E. Strzemieczna, Sztuczna inteligencja - Metody konstrukcji i analizy systemów eksperckich. 9. J.J. Mulawka, Systemy ekspertowe. 10. Roman Wantoch-Rekowski , Sieci neuronowe w zadaniach-perceptron wielowarstwowy 11. Russel Norvig, Artificial intelligence a modern approach.
Learning outcomes:	Knowledge: Student knows the basic concepts of machine learning and the artificial neural networks Skills: Student can apply machine lrearning techniques to practical problems. Attitudes: 1 recognizes the importance of machine learning methods in modern data analysis 2 appreciates the work in deepening their knowledge and skills in the area of machine learning
Assessment methods and assessment criteria:	The mark is an average of the result of the theoretical test and the solution of a practical problem.
Practical placement:	None

This course is not currently offered.

Course descriptions are protected by copyright.
Copyright by University of Warsaw.