Tool for connectivity-based parcellation
Python software package
We have created a new python tool for connectivity based parcellation.
[Read More]
We use machine learning methods to answer neuroscientific questions with a focus on macro-scale organization and functioning of the human brain.
We are located in the Forschungszentrum Jülich in Germany and are part of the
Brain and Behaviour (INM-7) institute and the Institute of Systems Neuroscience. Find out
more about us.
See the posts by tag.
Rank selection in NMF
systematic comparison and a new metric
Model selection in unsupervised learning is a long standing problem. Here we looked at the specific case of non-negative matrix factorization (NMF) and compared different ways to select its rank. We also propose a new method based on generalizatbility of a solution on unseen data.
[Read More]