Learning Complex Cell Invariance From Natural Videos: A Plausibility Proof

Free registration required

Executive Summary

Neuroscience has revealed many properties of neurons and of the functional organization of visual cortex that are believed to be essential to human vision, but are missing in standard artificial neural networks. Equally important may be the sheer scale of visual cortex requiring 1 petaflop of computation. In a year, the retina delivers 1 petapixel to the brain, leading to massively large opportunities for learning at many levels of the cortical system. The authors describe work at Los Alamos National Laboratory (LANL) to develop large-scale functional models of visual cortex on LANL's Roadrunner petaflop supercomputer. An initial run of a simple region VI code achieved 1.144 petaflops during trials at the JBM facility in Poughkeepsie, NY (June 2008).

  • Format: PDF
  • Size: 1771.52 KB