2 October 2006 Biomimetic sensory abstraction using hierarchical quilted self-organizing maps
Author Affiliations +
Proceedings Volume 6384, Intelligent Robots and Computer Vision XXIV: Algorithms, Techniques, and Active Vision; 63840A (2006); doi: 10.1117/12.686183
Event: Optics East 2006, 2006, Boston, Massachusetts, United States
Abstract
We present an approach for abstracting invariant classifications of spatiotemporal patterns presented in a high-dimensionality input stream, and apply an early proof-of-concept to shift and scale invariant shape recognition. A model called Hierarchical Quilted Self-Organizing Map (HQSOM) is developed, using recurrent self-organizing maps (RSOM) arranged in a pyramidal hierarchy, attempting to mimic the parallel/hierarchical pattern of isocortical processing in the brain. The results of experiments are presented in which the algorithm learns to classify multiple shapes, invariant to shift and scale transformations, in a very small (7×7 pixel) field of view.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jeffrey W. Miller, Peter H. Lommel, "Biomimetic sensory abstraction using hierarchical quilted self-organizing maps", Proc. SPIE 6384, Intelligent Robots and Computer Vision XXIV: Algorithms, Techniques, and Active Vision, 63840A (2 October 2006); doi: 10.1117/12.686183; https://doi.org/10.1117/12.686183
PROCEEDINGS
10 PAGES


SHARE
KEYWORDS
Sensors

Neurons

Brain

Brain mapping

Data modeling

Visual process modeling

Visualization

RELATED CONTENT

Biological models for automatic target detection
Proceedings of SPIE (April 14 2008)
Information fusion via isocortex-based Area 37 modeling
Proceedings of SPIE (August 09 2004)
Interpretation of the function of the striate cortex
Proceedings of SPIE (April 14 2000)
Würfelspiel-based training data methods for ATR
Proceedings of SPIE (September 21 2004)
Modeling of functional brain imaging data
Proceedings of SPIE (March 22 1999)

Back to Top