Brain disorders are seen as one of the greatest threats to public health in the 21st century. To develop new treatments we need a fundamental understanding of brain organization and function. Parcellation of the human brain is a central key for understanding complex human behavior and also a major challenge in systems neuroscience. Machine learning has become a central element in deriving human brain parcellations. Here, we give an overview of machine learning approaches to functional connectivity parcellation of the human brain with a special emphasis on mixture models and Markov random fields.
More detail can easily be written here using Markdown and $\rm \LaTeX$ math code.