TEK9040 – Deep Learning for Autonomous Systems

After completing the course

• you have an overview of modern algorithms and architectures for deep learning with neural networks relevant to autonomous systems
• you have a thorough knowledge of recurrent neural networks and their extensions with memory and attention as well as Transformers
• you have a knowledge of selected advanced algorithms in deep reinforcement learning
• you are familiar with stochastic approaches to deep learning and Bayesian methods
• you are familiar with different learning techniques such as supervised and and unsupervised learning, self-supervised learning and meta-learning
• you know how autonomous systems can benefit from deep learning for understanding, decision-making and planning actions
• you know how modern tools, such as TensorFlow, are used to create important components of advanced autonomous systems

PhD candidates from the University of Oslo should apply for classes and register for examinations through Studentweb.

If a course has limited intake capacity, priority will be given to PhD candidates who follow an individual education plan where this particular course is included. Some national researchers’ schools may have specific rules for ranking applicants for courses with limited intake capacity.

PhD candidates who have been admitted to another higher education institution must apply for a position as a visiting student within a given deadline.

It is recommended that you have a good prior knowledge of linear algebra, statistics and calculus, from for example MAT1110 – Calculus and Linear Algebra / MAT1120 – Linear Algebra, STK1100 – Probability and Statistical Modelling.

The course builds on basic knowledge of machine learning and neural networks, for example from courses IN3050 – Introduction to Artificial Intelligence and Machine Learning / IN4050 – Introduction to Artificial Intelligence and Machine Learning or IN5400 – Machine Learning for Image Analysis (continued).

The course provides 3 hours of lectures per week throughout the semester.

There will be 3 compulsory practical exercises, which must be approved in order to take the final exam. As a PhD candidate you will in addition write an essay, which must be approved in order to take the final exam.

• There will be a final written examination, which counts 100% towards the final grade.

All compulsory exercises and other compulsory activities must be approved in order to take the exam.

It will also be counted as 1 of the 3 attempts to sit the exam for this course, if you sit the exam for the following course:

• TEK5040 – Deep Learning for Autonomous Systems

Students who can document a valid reason for absence from the regular examination are offered a postponed examination at the beginning of the next semester.

Re-scheduled examinations are not offered to students who withdraw during, or did not pass, the original examination.