Skill level: In its easy version the project involves good knowledge of Python and Git; in its difficult version, in which the contributor can perform the model inversion, knowledge of simulation-based inference and neural density estimators, parallel architecture, and toolboxes for Bayesian estimation is needed.
Required skills: Python and git required. Knowledge of (computational) neuroscience, BIDS format, Bayesian statistics, simulation-based inference and techniques such as Normalizing Flows is a plus.
Time commitment: Large (350h)
Forum for discussion
About: The contributor will create and test use cases, in the form of jupyter notebooks, for the application of Bayesian model inversion using simulation-based inference to neuroimaging data. Both models and data are hosted on EBRAINS.
Aims:
Use cases in form of notebooks.
Baseline goal: one use case. More advanced goals: more use cases, comparative tests of different models on same data, and/or of the same model on different data.
I’m an Engineering Technology student from KU Leuven. If I’m interested and work on this preliminary task, should I include how I went about this inside of my proposal?
I am writing to express my interest in contributing to the BrainHeart project as part of the GSOC 2025 program. I am currently a PhD student at IIT Gandhinagar in Gujarat, India. I completed my undergraduate studies in Biomedical Engineering, where I worked on a project focused on the computational modeling of neurons in Alzheimer’s disease.
Following my undergraduate work, I joined IIT Gandhinagar as a Research Fellow and later began my PhD in the Medical Ultrasound Engineering Lab under the guidance of Prof. Karla Mercado-Shekhar. My current research focuses on quantitative ultrasound for soft tissue characterization.
I have developed expertise in mathematical modeling, signal and image processing, and experimental work. I am familiar with several Matlab toolboxes for EEG and EMG data analysis, and I have also worked with fMRI data. Additionally, I have experience coding in Python for signal-processing tasks.
While I have not previously worked with Slurm or clusters, as most of my research is conducted on lab workstations, I am eager to learn if necessary. Regarding web development, I have knowledge of HTML and have assisted with setting up websites at my institute, giving me valuable experience in this area.
I am particularly interested in exploring the relationship between the temporal dynamics of heart rate and blood pressure with brain dynamics to better understand heart rate variability, blood pressure variability, and cerebral autoregulation.
I would be happy to discuss this further. Please let me know your thoughts.
Thanks for the interest. The fast implementation of differential equations in C++, or Python Numba is required. The scaling to HCP using Slurm will be the final step.
Hi,
Dilara here, I have emailed you today to be redirected back here, I would like to submit a proposal for this project, are there any preferred use cases for this? I have spotted VEP & MOBILE (epilepsy) data, or perhaps brain tumor or functional connectivity? Please let me know.