Visual recognition: neural networks

General data

Course ID:	1000-2M18RO
Erasmus code / ISCED:	11.3 The subject classification code consists of three to five digits, where the first three represent the classification of the discipline according to the Discipline code list applicable to the Socrates/Erasmus program, the fourth (usually 0) - possible further specification of discipline information, the fifth - the degree of subject determined based on the year of study for which the subject is intended. / (0612) Database and network design and administration The ISCED (International Standard Classification of Education) code has been designed by UNESCO.
Course title:	Visual recognition: neural networks
Name in Polish:	Rozpoznawanie obrazów: sieci neuronowe (wspólnie z 1000-318bVR)
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 and Machine Learning Specific programme courses of 2nd stage Bioinformatics
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:	English
Type of course:	elective monographs
Requirements:	Deep neural networks 1000-2M16GSN
Short description:	Almost every other day, we hear of innovations in the field of visual recognition. Automatic classification of images, object detection, action recognition in videos, scene understanding by autonomous cars and object tracing by drones are just a few examples of the what can be achieved with visual recognition methods. Recent developments in neural networks (aka deep learning) have significantly advanced the visual recognition field. The goal of this course is to teach about cutting-edge deep learning architectures for visual recognition, and how to implement, train and debug neural networks. Students will gain theoretical knowledge, information on the latest research in the field, and will gain practical skills.
Full description:	1. Introduction to Visual Recognition. 2. Image Classification, Loss Functions and Optimization. 3. Introduction to Neural Networks. 4. Convolutional Neural Networks. 5. Training Neural Networks. Deep Learning Hardware and Software. 6. Convolutional Neural Networks: Architectures. 7. Recurrent Neural Networks. 8. Object Detection, Action Recognition, Semantic and Instance Segmentation, Video Understanding. 9. Generative Models. 10. Visualizing and Understanding. 11. Reinforcement Learning.
Bibliography:	* R. Szeliski, Computer Vision: Algorithms and Applications, Springer Science & Business Media, 2010. * Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016.
Assessment methods and assessment criteria:	Laboratories: projects. Lecture: written exam.

This course is not currently offered.

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