Title :
Holographic graph neuron
Author :
Osipov, Evgeny ; Khan, Asad I. ; Amin, Anang
Author_Institution :
Dept. of Comput. Sci., Lulea Univ. of Technol., Luleå, Sweden
Abstract :
This article proposes the usage of Vector Symbolic Architectures for implementing Hierarchical Graph Neuron. The adoption of VSA representation maintains previously reported properties and performance characteristics of HGN and further makes it suitable for implementation in distributed wireless sensor networks of tiny devices.
Keywords :
content-addressable storage; neural nets; parallel processing; wireless sensor networks; HGN; VSA representation; distributed wireless sensor networks; hierarchical graph neuron; holographic graph neuron; vector symbolic architecture; Arrays; Hamming distance; Neurons; Pattern matching; Vectors; Graph Neuron; Hierarchical Graph Neuron; Holographic Graph Neuron;
Conference_Titel :
Computer and Information Sciences (ICCOINS), 2014 International Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4799-4391-3
DOI :
10.1109/ICCOINS.2014.6868350
