Large-scale functional models of visual cortex for remote sensing
- Los Alamos National Laboratory
- PORTLAND STATE UNIV.
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 {approx}1 petaflop of computation. In a year, the retina delivers {approx}1 petapixel to the brain, leading to massively large opportunities for learning at many levels of the cortical system. We 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 IBM facility in Poughkeepsie, NY (June 2008). Here, we present criteria for assessing when a set of learned local representations is 'complete' along with general criteria for assessing computer vision models based on their projected scaling behavior. Finally, we extend one class of biologically-inspired learning models to problems of remote sensing imagery.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC52-06NA25396
- OSTI ID:
- 978329
- Report Number(s):
- LA-UR-09-07673; LA-UR-09-7673; TRN: US201010%%49
- Resource Relation:
- Conference: 2009 38th IEEE Applied Imagery Pattern Recognition Workshop ; October 14, 2009 ; Washington, DC
- Country of Publication:
- United States
- Language:
- English
Similar Records
Deep learning as a tool for neural data analysis: Speech classification and cross-frequency coupling in human sensorimotor cortex
Noninvasive studies of human visual cortex using neuromagnetic techniques