Deep Learning
About the course
The course is available as a singular course.
Programstudents may register for the course through Studentweb. The registration deadline is September 1st/February 1st.
Other PhD students at UiT and external applicants may apply for admission through Søknadsweb, application code 9301. The application deadline is June 1st for the autumn semester and December 1st for the spring semester.
Deep Learning, a subfield of machine learning, has in recent years achieved state-of-the-art performance for tasks such as image classification, object detection and natural language processing. This course will study recent deep learning methodology such as e.g. convolutional neural networks, autoencoders and recurrent neural networks, will discuss in detail recent advances in the field, and will provide the students with the required background and up-to-date knowledge to implement, train and debug these models. There will be a significant practical component, where students will gain hands-on experience on contemporary problems. The course will in addition to deep learning algorithms contain elements of image processing, pattern recognition and statistics.
Admission requirements
PhD students or holders of a Norwegian master´s degree of five years or 3+ 2 years (or equivalent) may be admitted. PhD students must upload a document from their university stating that there are registered PhD students. This group of applicants does not have to prove English proficiency and are exempt from semester fee. Holders of a Master´s degree must upload a Master´s Diploma with Diploma Supplement / English PhD students at UiT The Arctic University of Norway register for the course through StudentWeb . External applicants apply for admission through SøknadsWeb. Application code 9303.
All external applicants have to attach a confirmation of their status as a PhD student from their home institution. Students who hold a Master of Science degree, but are not yet enrolled as a PhD-student have to attach a copy of their master's degree diploma. These students are also required to pay the semester fee.
Objectives of the course
Knowledge - The student is able to:
- describe fundamental deep learning techniques
- describe the development of deep learning
- discuss recent developments in the field and develop an understanding for when deep learning might not be the optimal methodology
- discuss advanced deep learning approaches for specialized settings
Skills - The student is able to:
- explain the general idea behind deep learning as well as specific algorithms that are being used
- apply the learned material to new advanced applications or problem settings
- use and further develop deep learning methodology for research and industrial settings using software libraries such as e.g. Theano or TensorFlow
- carry out an advanced deep learning project in an individual manner
- make independent choices about methodology and methods of analysis and performance assessment for a given application or problem setting
General competence - The student is able to:
- give an interpretation of recent developments and provide an intuition of the open questions in the field
- give an account of the impact of deep learning in modern society and communicate this to non-experts
- implement and apply advanced deep learning methods to applications of her/his choosing
Prerequisites
Anbefalte forkunnskaper
FYS-2010 Image Analysis, FYS-2021 Machine Learning, FYS-3012 Pattern recognition
Credit reduction
If you pass the examination in this course, you will get an reduction in credits (as stated below), if you previously have passed the following courses:
- FYS-3033 Deep learning 8 ects
Teaching methods
Lectures: 30 hours
Exercises: 30 hours
Language of instruction and examination
The language of instruction is English and all of the syllabus material is in English. Examination questions will be given in English, but may be answered either in English or a Scandinavian language.Schedule
The schedules are normally finalized and published well in advance of the start of the semester, often a few weeks beforehand. This gives students the opportunity to organize their studies and prepare for upcoming activities.
It is recommended to check the schedule regularly, as changes may occur.
Examination
| Oral exam | Duration: 40 Minutes |
Grade: Passed / Not Passed |
To take an examination, the student must have passed the following coursework requirements
| Short written assignment, implementation of fundational deep learning algorithms | Grade: Approved – not approved |
| Large practical project with impelmentation of state-of-the-art deep learning | Grade: Approved – not approved |
| Presentation on their PhD project and how deep learning can be used in their project | Grade: Approved – not approved |
Everything you need to know about before, during, and after the exam; registration, absence, appeals, and diplomas: UiT Exams homepage
More info about the coursework requirements
Students are required to deliver two presentations of their fellow students over the course of the project period. The first presentation shall address the project idea and research question, while the second shall provide an account of the project's progress and development.
Fellow students are expected to assume the role of evaluators two times during the project period and to provide constructive and academically grounded feedback during the presentations.
In addition, students are required to submit a concise written report on the project. The work process will form part of the basis for the assessment of the coursework requirement. The project as a hole will also constitute part of the foundation for the oral examination.