Loading...
Loading...

Go to the content (press return)

LEGION-based image segmentation by means of spiking neural networks using normalized synaptic weights implemented on a compact scalable neuromorphic architecture

Author
Sánchez , G.; Madrenas, J.; Cosp, J.
Type of activity
Journal article
Journal
Neurocomputing
Date of publication
2019-01-01
Volume
352
First page
106
Last page
120
DOI
10.1016/j.neucom.2019.04.037
Project funding
Sistema en chip micro-electro-mecánico (MEMSOC)
Synergic and Efficient Multi-MEMS for Internet of Things Integrated on CMOS
Repository
http://hdl.handle.net/2117/186127 Open in new window
URL
https://www.sciencedirect.com/science/article/pii/S0925231219306186 Open in new window
Abstract
LEGION (Locally Excitatory, Globally Inhibitory Oscillator Network) topology has demonstrated good capabilities in scene segmentation applications. However, the implementation of LEGION algorithm requires machines with high performance to process a set of complex differential equations limiting its use in practical real-time applications. Recently, several authors have proposed alternative methods based on spiking neural networks (SNN) to create oscillatory neural networks with low computational...
Citation
Sánchez , G.; Madrenas, J.; Cosp, J. LEGION-based image segmentation by means of spiking neural networks using normalized synaptic weights implemented on a compact scalable neuromorphic architecture. "Neurocomputing", 1 Gener 2019, vol. 352, p. 106-120.
Keywords
FPGA, LEGION, SIMD architecture, Spiking neural networks
Group of research
CETpD - Technical Research Centre for Dependency Care and Autonomous Living
ISSET - Integrated Smart Sensors and Health Technologies

Participants

Attachments