Translator Disclaimer
Presentation
27 April 2020 Image mirror symmetry density enabled by delay and coincidence detection in spiking neural networks (Conference Presentation)
Author Affiliations +
Abstract
Neuromorphic computing has made tremendous advances in computing efficiency by modeling computers after the brain primarily by applying a spiking model of information. Spiking models inherently maximize efficiency in noisy environments by placing the energy of the signal in a minimal time. However, many neuromorphic computing models ignore time delay between nodes, choosing instead to approximate connections between neurons as instantaneous weighting. With this assumption, many complex time interactions of spiking neurons are lost. Here, we show that the coincidence detection property of a spiking-based feed-forward neural network enables mirror symmetry. Testing this algorithm exemplary on geospatial satellite image data sets reveals how symmetry density enables automated recognition of man-made structures over vegetation. We further demonstrate that the addition of noise improves feature detectability of an image through coincidence point generation.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Volker J. Sorger "Image mirror symmetry density enabled by delay and coincidence detection in spiking neural networks (Conference Presentation)", Proc. SPIE 11423, Signal Processing, Sensor/Information Fusion, and Target Recognition XXIX, 1142315 (27 April 2020); https://doi.org/10.1117/12.2559081
PROCEEDINGS
PRESENTATION


SHARE
Advertisement
Advertisement
Back to Top