Choose department Department of Computer Science Department of Business and Economics Department of Law Department of Engineering Department of Preliminary Studies MBA Department of Applied Engineering Department of Sport Science Department of Psychology MPM Department of Computer Science Dean: Dr. Henning Arnór Úlfarsson Email: ru@ru.is Website: http://www.ru.is/td Teachers View Choose major BSc in Computer Science BSc in Computer Science - Business Minor MSc in Computer Science BSc in Software Engineering MSc in Software Engineering PhD in Computer Science BSc in Discrete Mathematics and Computer Science Diploma in Computer Science-on campus Diploma in Computer Science in collaboration with UNAK Diploma in Computer Science - Part time Exchange Studies - BSc School of Computer Science Exchange Studies - MSc School of Computer Science BSc in Computer Science at UNAK MSc in Data Science MSc in Applied Data Science MSc in Artificial Intelligence and Language Technology MSc in Digital Health MSc in Artificial intelligence MSc in Cybersecurity MSc in Computer Science Semesters: 4 Years: 2 ETCS: 120 About major Meistaranám í tölvunarfræði hentar þeim sem vilja þróa sína sérþekkingu eftir áhugasviði. Nemendur hafa mikið val og sveigjanleika í náminu, meðal viðfangsefna eru gervigreind, tölvuöryggi, þjarkafræði, sýndarheimar og gagnagrunnar. Learning Outcomes View Education cycle 2

Legend Mandatory course on major Teaching language Optional course on major Prerequisites for course

Vorönn/Spring 2026 Business Intelligence I-707-VGBI ECTS 6 Functional Programming T-209-FUPR ECTS 6 Operating Systems T-215-STY1 ECTS 6 Programming Languages T-501-FMAL ECTS 6 Software Maintenance T-533-VIHU ECTS 6 Mechatronics II T-535-MECH ECTS 6 Artificial Intelligence T-622-ARTI ECTS 6 Advanced Game Design & Development T-634-AGDD ECTS 6 Game Engine Architecture T-637-GEDE ECTS 6 Research Methodology T-701-REM4 ECTS 8 Speech Processing T-715-SPPR ECTS 6 Foundations of Data Privacy: A Legal and Technical Perspective T-722-PRIV ECTS 8 How Misinformation Spreads: Technology, Belief, and Behaviour T-727-MSTB ECTS 6 Empirical Research in Software Engineering, Information Systems, and Human-Computer Interaction T-741-ERSE ECTS 8 Cyber Security Management & Compliance in Practice T-746-COPS ECTS 8 Modern Binary and Microarchitecture Exploitation Techniques and Mitigations T-747-EXPL ECTS 6 Independent Study 1 T-749-INDS ECTS 6 Big Data Management T-764-DATA ECTS 8 Applied Data Science T-786-APDS ECTS 6 MSc Thesis (30 ECTS) T-810-MTPR ECTS 24 Creating a Complete Business Plan for a Technical Idea - Entrepreneurship and the Innovation Process T-814-INNO ECTS 8 Deep Learning T-820-DEEP ECTS 8 Year 1. year Semester Spring 2026 Level of course N/A Type of course Elective Prerequisites No prerequisites. Schedule Term: 12-week Level: MSc Breadth Requirement: Theory course Recommended Requirements:Machine learning MSc Type: Mandatory for MSc Data Science Lecturer Giovanni Apruzzese Content The course gives a comprehensive overview of the fundamentals of deep learning and some of its applications. We will cover feed-forward, convolutional, and sequential neural networks, and how they compare to traditional machine-learning (ML) algorithms (eg, random forests) on a practical level.  Additionally, we will discuss practical methodologies for developing deep-learning (DL) models, emphasizing "dos and don´ts" and "pitfalls" that must be known to proficiently use these methods in the real world.  Moreover, we will explore some applications of DL and ML, highlighting where it is sensible to opt for DL ​​​​over ML methods. Finally, we will examine some security and privacy aspects of various learning algorithms, which are often neglected in operational contexts.  The course has a sizeable hands-on part where students use widely-used DL frameworks and techniques to solve interesting problems. The course will, in addition, be strongly rooted on the findings of recent research articles. Learning outcome - Objectives The learning outcomes of the course are for participating students to be able to: Demonstrate a solid background in the fundamentals of deep learning (DL) and how it compares with traditional machine-learning (ML) methods. Read, comprehend, and implement the methods discussed on scholarly articles in the field Use well-known DL platforms/frameworks to build, train, and evaluate deep neural networks. Show a critical and security-centered mindset, meant to be used wherever deployment of DL methods is conceivable, so as to facilitate development of trustworthy DL-based systems and applications. Course assessment Assessment Breakdown: Quizzes: 27%  Reports: 27%  Presentations: 18%  Code Assignments: 18%  Oral Q&A: 10%  Total: 100% To be more specific, the course will involve both short exams in the form of "quizzes" to be done (on paper) during some of the lecture days, and which collectively make up 27% of the grade); as well as "project work", meant to be done in pairs, which encompasses a variety of activities (i.e., writing of technical reports, presenting the results, answering questions, as well as development of source code), which makes up the remaining 73% of the grade. Reading material No reading material found. Teaching and learning activities •  Parts of the course will be based on the "Deep Learning" textbook by I. Goodfellow, Y. Bengio, and A. Courville (MIT Press, 2016);  http://www.deeplearningbook.org.  •  The course will also rely on scientific articles: the lecturer will provide such articles to the students free of charge (although students are encouraged to read additional related works).   •  Lecture slides and exemplary notebooks will be provided by the lecturer .  •  Some lectures will be recorded and provided to the students     •  The lecturer will also provide additional resources with tutorials​         Language of instruction English MSc Thesis Defence (30 ECTS) T-820-MDPR ECTS 6 MSc Thesis - Part I T-830-MSTR ECTS 30 MSc Thesis - Part II T-835-MTRH ECTS 24 MSc Thesis Defence (60 ECTS) T-840-MDRS ECTS 6 Entrepreneurial Finance V-733-ENTR ECTS 7,5 Entrepreneurship and Starting New Ventures X-204-STOF ECTS 6 Exchange Studies X-699-EXCH ECTS 30 Haustönn/Fall 2026 Mathematical Programming E-402-STFO ECTS 6 Operation Research T-403-ADGE ECTS 6 Effective Programming and Problem Solving T-414-AFLV ECTS 6 Computer Security T-417-TOOR ECTS 6 Simulation T-502-HERM ECTS 6 Machine Learning T-504-ITML ECTS 6 Computer Graphics T-511-TGRA ECTS 6 Cryptography and Number theory T-513-CRNU ECTS 6 Theory of Computation T-519-STOR ECTS 6 Cyber Physical Systems T-535-CPSY ECTS 6 Compilers T-603-THYD ECTS 6 Computer Game Design & Development T-624-CGDD ECTS 6 Software Engineering II - Testing T-631-SOE2 ECTS 6 Digital Health T-702-MDGH ECTS 8 Applied Statistics for Data Science T-705-ASDS ECTS 8 AI, Ethics and Society T-709-AIES ECTS 8 Machine Learning in Cyber Security T-710-MLCS ECTS 8 Fundamentals of Machine Learning T-711-FOML ECTS 8 Applications of Digital Health T-712-MADH ECTS 8 Empirical Reasoning AI Systems T-713-MERS ECTS 8 Advanced Topics in Distributed Systems T-714-FINT ECTS 6 Natural Language Processing T-725-MALV ECTS 8 Introduction to computer-assisted proof T-733-ICAP ECTS 6 Software Project Management T-740-SPMM ECTS 8 Computer Security: Defence Against the Dark Arts T-742-CSDA ECTS 8 Independent Study 1 T-749-INDS ECTS 6 Statistical modelling & computation T-750-SMAC ECTS 6 An exploration to the ethical issues of emerging technology through the lens of Black Mirror T-777-BLMR ECTS 6 MSc Thesis (30 ECTS) T-810-MTPR ECTS 24 Optimization Methods T-810-OPTI ECTS 8 Applied Probability T-811-PROB ECTS 8 Managing Research and Development - Methods and Models T-814-PROD ECTS 8 MSc Thesis Defence (30 ECTS) T-820-MDPR ECTS 6 MSc Thesis - Part I T-830-MSTR ECTS 30 MSc Thesis - Part II T-835-MTRH ECTS 24 MSc Thesis Defence (60 ECTS) T-840-MDRS ECTS 6 Vorönn/Spring 2027 Mechatronics II T-535-MECH ECTS 6 MSc Thesis (30 ECTS) T-810-MTPR ECTS 24 Creating a Complete Business Plan for a Technical Idea - Entrepreneurship and the Innovation Process T-814-INNO ECTS 8 MSc Thesis Defence (30 ECTS) T-820-MDPR ECTS 6 MSc Thesis - Part I T-830-MSTR ECTS 30 MSc Thesis - Part II T-835-MTRH ECTS 24 MSc Thesis Defence (60 ECTS) T-840-MDRS ECTS 6