Braincoder is a package to fit encoding models to neural data (for now fMRI) and to then invert those models to decode stimulus information from neural data.
- Official source code repo: https://github.com/Gilles86/braincoder/tree/main
- HTML documentation (stable release): https://braincoder-devs.github.io/
Note that you need an environment with both tensorflow-probability and tensorflow.
(Only do this if you don't have conda installed)
I recommend using miniforge,
make sure you use the mamba-solver and set channel-priority to strict:
# Install mamba solver and set channel priority
conda install mamba -n base -c conda-forge
conda config --set channel_priority strict.Here we create a new environment called braincoder with the required packages:
mamba create --name braincoder tensorflow-probability tensorflow -c conda-forge
mamba activate braincoder
pip install git+https://github.com/Gilles86/braincoder.gitIf you use Braincoder in your research, please cite it using the following information:
> de Hollander, G., Renkert, M., Ruff, C. C., & Knapen, T. H. (2024). Braincoder: A package for fitting encoding models to neural data and decoding stimulus features. Zenodo. DOI: 10.5281/zenodo.10778413.
Alternatively, use this BibTeX entry:
@software{deHollander2024braincoder,
author = {Gilles de Hollander and Maike Renkert and Christian C. Ruff and Tomas H. Knapen},
title = {braincoder: A package for fitting encoding models to neural data and decoding stimulus features},
year = {2024},
publisher = {Zenodo},
doi = {10.5281/zenodo.10778413},
url = {https://github.com/Gilles86/braincoder}
}By citing this software, you help support open-source development and proper crediting in academic research.
Please have a look at the tutorials to get started.