University of Warsaw - Central Authentication System

Visual recognition

General data

Course ID:	1000-318bVR
Erasmus code / ISCED:	11.3 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:	Visual recognition
Name in Polish:	Visual recognition
Organizational unit:	Faculty of Mathematics, Informatics, and Mechanics
Course groups:	(in Polish) Przedmioty obieralne na studiach drugiego stopnia na kierunku bioinformatyka Elective courses for Computer Science Obligatory courses for 1st year Machine Learning Specific programme courses of 2nd stage Bioinformatics
ECTS credit allocation (and other scores):	5.00 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:	English
Type of course:	elective monographs
Requirements:	Deep neural networks 1000-2M16GSN
Short description:	The goal of the course is to present deep learning architectures as well as to teach implementation, training and debugging own neural networks dedicated to visual recognition. Students gain theoretical knowledge, information on the state of the current research in the domain and obtain practical skills in visual recognition.
Full description:	1. Introduction to Visual Recognition (classic methods: SIFT, Hough transform). 2. Convolutional Neural Networks - recap. 3. Visualising and Understanding. 4. Object Detection. 5. Semantic and Instance Segmentation. 6. Video understanding. 7. 3D vision. 8. Generative models.
Bibliography:	http://www.deeplearningbook.org/
Learning outcomes:	Knowledge: the student * has based in theory and well organized knowledge of problems of image classification and object detection [K_W12]. Abilities: the student is able to * create a developed solution in the domain of image classification and object detection [K_U15]. Social competences: the student is ready to * critically evaluate acquired knowledge and information [K_K01]; * recognize the significance of knowledge in solving cognitive and practical problems and the importance of consulting experts when difficulties arise in finding a self-devised solution [K_K02]; * think and act in an entrepreneurial way [K_K03].
Assessment methods and assessment criteria:	Laboratories: programming projects. Lectures: written examination

Classes in period "Summer semester 2023/24" (in progress)

Time span:	2024-02-19 - 2024-06-16	Selected timetable range: weekly course term Navigate to timetable MO TU WYK LAB LAB W TH FR LAB
Type of class:	Lab, 30 hours more information Lecture, 30 hours more information
Coordinators:	Piotr Biliński
Group instructors:	Piotr Biliński, Spyridon Mouselinos, Marcin Możejko, Konrad Staniszewski
Students list:	(inaccessible to you)
Examination:	Examination

Classes in period "Summer semester 2024/25" (future)

Time span:	2025-02-17 - 2025-06-08	Selected timetable range: weekly course term Navigate to timetable
Type of class:	Lab, 30 hours more information Lecture, 30 hours more information
Coordinators:	Piotr Biliński
Group instructors:	Piotr Biliński, Jacek Cyranka, Spyridon Mouselinos, Alicja Ziarko
Students list:	(inaccessible to you)
Examination:	Examination

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