Email updates

Keep up to date with the latest news and content from BMC Neuroscience and BioMed Central.

This article is part of the supplement: Twenty First Annual Computational Neuroscience Meeting: CNS*2012

Open Access Open Badges Poster presentation

GPU facilitated unsupervised visual feature acquisition

Blake Lemoine* and Anthony Maida

Author Affiliations

Center for Advanced Computer Studies, University of Louisiana, Lafayette, LA 70503, USA

For all author emails, please log on.

BMC Neuroscience 2012, 13(Suppl 1):P87  doi:10.1186/1471-2202-13-S1-P87

The electronic version of this article is the complete one and can be found online at:

Published:16 July 2012

© 2012 Lemoine and Maida; licensee BioMed Central Ltd.

This is an Open Access article distributed under the terms of the Creative Commons Attribution License (, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Poster presentation

This paper examines the effects of parallelizing an unsupervised feature acquisition algorithm using General-Purpose computing on Graphics Processing Units (GPGPU). Previous work in feature learning has established the effectiveness of hierarchical learning methods that refine large quantities of elementary features into small numbers of intermediate-level features. Some of the most effective of these methods alternate between template matching layers that combine features and sub-sampling layers that perform feature scale and/or position invariance. This approach is inspired by the mammalian ventral visual pathway. One such approach that produces highly informative features is a spiking convolutional network trained with STDP-based learning [1]. When using a serial implementation, however, this approach is costly in time and consequently is difficult to scale to a large library of internally complex features. The present paper demonstrates that GPGPU parallelism can be leveraged to overcome the scaling limitations of the serial version. Highly informative features can then be generated in large quantities. By scaling the number of features learned the maximum complexity of learnable classes is significantly increased.


  1. Masquelier T, Thorpe S: Unsupervised learning of visual features through spike timing dependent plasticity.

    PLoS Computational Biology 2007., 3 OpenURL