Graph-based Learning for Neuronal Morphologies
Given 3D shapes of individual neurons, the goal of the project is to use state-of-the-art graph neural networks to learn a low-level representation of the morphologies of different cell types with the help of self-supervised learning. The learned representation will then be used in a subsequent clustering step to classify the cell types and potentially other attributes of the neurons.
Requirements
- Good mathematical understanding (in particular statistics and linear algebra)
- Python programming (including Pytorch)
- Experience in machine learning
Contact
Marissa Weis