STNMF with AF-HALS

A fast and versatile implementation of spike-triggered non-negative matrix factorization (STNMF) based on accelerated fast hierarchical alternating least squares (AF-HALS) algorithms.

This Python package allows fast inference of receptive-field subunits from the spiking responses of retinal ganglion cells including methods of hyperparameter tuning.

Described in the paper:

Zapp SJ, Khani MH, Schreyer HM, Sridhar S, Ramakrishna V, Krüppel S, Mietsch M, Protti DA, Karamanlis D, Gollisch T: Accelerated spike-triggered non-negative matrix factorization reveals coordinated ganglion cell subunit mosaics in the primate retina

Documentation

The documentation is available at https://stnmf.readthedocs.io.

Installation

Install using pip from command-line:

pip install stnmf

Contact

For feedback and bug reports, please use the Github issue tracker.