The overall goal of the course is to provide the student with an overview of missing data and their origins. After the course, the student will be able implement and evaluate common and advanced methods to deal with missing data. En studerende, der fuldt ud har opfyldt kursets mål, vil kunne:

• Describe the typical types of missing data
• Describe reasons and origins of missing data
• Give an overview of current state-of-the-art methods to deal with missing data
• Describe the concept of generative models and their typical use
• Give an overview of state-of-the-art approaches to data augmentation
• Implement and test a Python based framework for dealing with missing data
• Implement and test a Python based framework for data augmentation
• Implement and test a Python based framework for generative modelling

Missing data is a common problem in image processing and in general AI based methods. The source can be, for example, occlusions in 3D computer vision problems, poorly dyed tissue in biological applications, missing data points in long-term observations, or perhaps there is just too little annotated data for a deep-learning model to properly converge. On this Ph. D. summer school, you will learn some of the modern approaches to handling the above-mentioned problems in a manner compatible with modern machine learning methodology.

This summer school will give an introduction to the state-of-the-art for handling too little or missing data in image processing tasks. The topics include data augmentation, density estimation, and generative models. The course will include project work, where the participants make a small programming project relating their research to the summer school’s topics. Please see the homepage for details. 13. marts, 2024