Large Scale Computing Models

Spiking Models



Research in the News

Job Opportunities

PANN Petascale Artificial Neural Network

PANN is an artificial neural network model of visual cortex that enables petascale simulation of mammalian vision (retina, LGN, and visual cortex ventral pathway V1 -> V2 -> V4 -> IT), using large amounts of image and video data.

PANN uses a biologically-inspired hierarchical feed-forward architecture in the family of Neocognitron/HMAX models (Fukushima [1], Poggio et al.[2])

Figure: PANN model of Visual Cortex. PANN is a model of mammalian visual processing through retina, LGN, and visual cortex ventral pathway (V1 -> V2 -> V4 -> IT). Image classification by frontal cortex is modeled using a conventional machine learning algorithm (e.g., SVM).

Initial results with PANN are available here.


[1] K. Fukushima, Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biological Cybernetics, 36(4), pp. 193-202 (April 1980). [LINK]

[2] T. Serre, A. Oliva and T. Poggio. A feedforward architecture accounts for rapid categorization. Proceedings of the National Academy of Science, 104(15), pp. 6424-6429, April 2007. [LINK]

[3] Steven Brumby, Luis Bettencourt, Michael Ham, Ryan Bennett, and Garrett Kenyon, Quantifying the difficulty of object recognition tasks via scaling of accuracy versus training set size, Computational and Systems Neuroscience (COSYNE) 2010, 25-28 Feb 2010, Salt Lake City, Utah [LINK]

[4] Will Landecker, Steven Brumby, Mick Thomure, Cristina Rinauldo, Garrett Kenyon, Luis Bettencourt, and Melanie Mitchell, Visualizing Classification Decisions of Hierarchical Models of Cortex, Computational and Systems Neuroscience (COSYNE) 2010, 25-28 Feb 2010, Salt Lake City, Utah [LINK]

[5] L. M. Bettencourt, S. Brumby, V. Gintautas, M. I. Ham, S. Barr, P. Loxley, K. Sanbonmatsu, S. Swaminarayan, J. George, G. Kenyon, I. Nemenman. Image categorization through large-scale hierarchical models of the primate visual cortex., Program No. 652.2/Y13. Society for Neuroscience 2009, Oct 17-21, 2009, Chicago IL.

[6] Steven P. Brumby, Garrett Kenyon, Will Landecker, Craig Rasmussen, Sriram Swaminarayan, and Luis M. A. Bettencourt, Large-scale functional models of visual cortex for remote sensing, 2009 38th IEEE Applied Imagery Pattern Recognition, Vision: Humans, Animals, and Machines, Cosmos Club, Washington DC October 14-16, 2009 [LINK]