BrainIAK applies advanced machine learning methods and high-performance computing to analyzing neuroimaging data. It is tightly integrated with SciKit-Learn, and includes modules for Full Correlation Matrix Analysis (FCMA), Multi-voxel Pattern Analysis (MVPA), a suite of methods for Shared Response Modeling (SRM), Topographic Factor Analysis (TFA), Bayesian-derived methods for Representational Similarity Analysis (RSA), and more.
The easiest way to get started is via Conda. We provide a Docker image and a pip package (which requires extra steps) as alternatives.
Method 1: Conda (recommended) # 1. Install Miniconda (Mac, Win, Linux) # 2. Create a Conda environment (link) > conda create -n venv # 3. Activate the Conda environment (link) > source activate venv # 4 Install Brainiak > conda install -c brainiak -c defaults -c conda-forge brainiak
Method 2: Docker # 1. Install Docker (Mac, Win, Linux) # 2. Run the following commands: > docker pull brainiak/brainiak > docker run -it -p 8888:8888 -v brainiak:/mnt --name demo brainiak/brainiak > python3 -m notebook --allow-root --no-browser --ip=0.0.0.0 # 3. Visit http://localhost:8888
Method 3: pip # 1. Install BrainIAK requirements # 2. Run the following command: > python3 -m pip install -U brainiak
FCMA: Full correlation matrix analysis.
MVPA: Multi-voxel pattern analysis.
SRM: A suite of methods for Shared Response Modeling.
TFA: Topographic factor analysis.
RSA: Bayesian-derived methods for Representational Similarity Analysis
Other: MPI-enabled searchlight, event segmentation, fMRI simulation, and more