BrainIAK at SfN 2017

BrainIAK is a Python package for high-performance neuroimaging analysis. Below are the six posters associated with the BrainIAK project that will appear at SfN 2017 along with several code examples. The easiest way to get started with the examples is via a Docker container:
  1. Install Docker (Windows, macOS, or Ubuntu).
  2. Run the following commands in your terminal (or follow the documentation):
    • 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 in your browser.
For the full BrainIAK feature set, including scalability, please
  1. Install the appropriate requirements
  2. Install BrainIAK via pip install brainiak
Please contact us if you need help.

Posters at SfN 2017

260.04: Using realistic, synthetic fMRI data to validate Topological Data Analysis as a tool for fMRI
Cameron T. Ellis, Michael Lesnick, Bryn Keller, Chris Baldassano, Anna Schapiro, Jonathan D. Cohen
contact (pdf, example)


260.05: When temporal similarity is mistaken for representational similarity: A Bayesian approach to reduce bias in RSA of fMRI data
Ming Bo Cai, Nicolas W. Schuck, Jonathan W. Pillow, Yael Niv
contact (pdf, example)


260.06: Real-time fMRI analysis in the cloud
Daniel C. Suo, J. Benjamin Hutchinson, Megan T. DeBettencourt, Anne C. Mennen, Yida Wang, Theodore L. Willke, Nicholas B. Turk-Browne, Kenneth A. Norman, Jonathan D. Cohen, Kai Li
contact (pdf, example)


260.07: Brain Imaging Analysis Kit: Advanced fMRI analysis at scale
Mihai Capotă, Theadore L. Willke, Kenneth A. Norman, Jonathan D. Cohen, Nicholas B. Turk-Browne
contact (pdf, example)

Searchlight figure details: Configuration: 2 Intel Xeon® CPUs E5-2699 v4 (22 cores, 44 hardware threads each), 128 GiB RAM, Intel® Omni-Path Card (100 Gbit/s), Intel® SSD 540s Series (480 GB), CentOS 7.2.1511 (with Linux 3.10), Intel® MPI Library 2017 Update 2, Python 3.4.

Intel and Xeon are trademarks of Intel Corporation or its subsidiaries in the U.S. and/or other countries.


260.08: Multi-subject fMRI data factor analysis using BrainIAK
Hejia Zhang, Po-Hsuan Chen, Peter J. Ramadge
contact (pdf, paper)


260.09: Matrix-normal models for fMRI analysis
Michael Shvartsman, Narayanan Sundaram, Mikio C. Aoi, Adam Charles, Theodore L. Willke, Jonathan D. Cohen
contact (pdf, paper)


  • About
  • BrainIAK is the result of an ongoing collaboration among the Brain-Inspired Computing Lab at Intel, the Princeton Neuroscience Institute, and other institutions. All parties maintain a firm commitment to community-developed open-source software.

  • Copyright © 2017 Intel Corporation and Princeton University. All Rights Reserved.