Course - Deep Learning for Visual Computing - IMT4392
IMT4392 - Deep Learning for Visual Computing
About
Examination arrangement
Examination arrangement: Approved report
Grade: Letter grades
| Evaluation | Weighting | Duration | Grade deviation | Examination aids |
|---|---|---|---|---|
| Approved report | 100/100 |
Course content
- Introduction to deep learning (DL) - Deep neural networks (DNN) - Convolutional neural network (CNN) - Recurrent neural network (RNN) - Introduction to visual computing - Still-image and video processing - Enhancement, filtering and segmentation - Selected case studies on DL for visual computing
Learning outcome
On successful completion of the module, students will be able to - Possess advanced knowledge within the area of Deep learning for visual computing. Understand the meaning of concepts such as Multi-layer perceptron, Dropout, Convolutional networks. - Possess specialized insight and good understanding of the research frontier of Deep learning techniques and algorithms for visual computing applications.
Skills and general competence: - Be able to use relevant and suitable methods when carrying out further research and development activities in the area of Deep learning for visual computing - Be able to critically review relevant literature when solving the assigned problem or topic. - Is able to communicate academic issues, analysis, and conclusions, with specialists in the field, in oral and written forms - Is experienced in acquiring new knowledge and skills in a self-directed manner - Develop a course project based on an application scenario and implement several of the algorithms to solve practical problems. The students will also enhance their programming skills in Python and Tensorflow.
Learning methods and activities
Lectures, exercises, self-study, presentation and obligatory course project. This course will focus on practical implementation of Deep Learning for visual computing.
Further on evaluation
Project report and presentation of the project work
Specific conditions
Admission to a programme of study is required:
Applied Computer Science (MACS)
Applied Computer Science (MACS-D)
Colour in Science and Industry (COSI) (MACS-COSI)
Computational Colour and Spectral Imaging (MSCOSI)
Recommended previous knowledge
AI or Machine learning (recommended). In order to accommodate students with no or little experiences with Machine learning, we will make use of some online tutorial materials (videos and exercises) at the beginning and set up checkpoint for these basics so that everyone will have the necessary introductory knowledge to work on the course project.
Course materials
There is no required textbook and students should be able to learn everything from the suggested materials and mentoring during the course project.
No
Version: 1
Credits:
7.5 SP
Study level: Second degree level
Term no.: 1
Teaching semester: AUTUMN 2022
Language of instruction: English
Location: Gjøvik
- Computer Science
Examination
Examination arrangement: Approved report
- Term Status code Evaluation Weighting Examination aids Date Time Examination system Room *
-
Autumn
ORD
Approved report
100/100
Release
2022-12-01Submission
2022-12-09
09:00
INSPERA
23:59 -
Room Building Number of candidates
- * The location (room) for a written examination is published 3 days before examination date. If more than one room is listed, you will find your room at Studentweb.
For more information regarding registration for examination and examination procedures, see "Innsida - Exams"