Master thesis for visual models of whole brain ultra-sound recordings
How to Apply
[ML Master]
Required Materials
- What you are studying (e.g. "Master in Applied Data Science")
- Statement of motivation (max 300 words) outlining your personal interest in our research areas
- A short list of which relevant skills you have and which you would like to acquire
- A list of courses you have taken and corresponding grades
- Known programming languages and experience
- Possible start date
If applying with your own project idea
- A concise research proposal (max 300 words) on a project you would be interested in working on
Project Description
In collaboration with Prof. Emilie Mace, we are looking for a master student to develop machine learning models to predict visually driven activity in whole brain ultra-sound recordings in mice. With functional ultrasound imaging, it is possible to record whole brain activity in awake mice at high spatial resolution (100 µm). Ultrasound measures the change in blood flow related to activity in the brain. It is particularly suited to record activity in deeper areas of the brain, which are not easily accessible with traditional large scale recordings methods.
The goal of the thesis is to develop a model that can predict the activity of visual areas in the brain in response to natural images or videos. The basis of these models will be deep convolutional recurrent networks.
Interested students should know Python and have knowledge in machine learning and ideally attended B.Inf.1236: Machine Learning and B.Inf.1237: Deep Learning. Knowledge in neuroscience is a plus, but not required.
