Pruning self-organizing maps for cellular hardware architectures

Upegui, Andres (School of Engineering, Architecture and Landscape (hepia), HES-SO // University of Applied Sciences Western Switzerland) ; Girau, Bernard (Université de Lorraine, CNRS, LORIA, Nancy, France) ; Rougier, Nicolas (Inria Bordeaux Sud-Ouest - LaBRI / Université de Bordeaux, Bordeaux, France) ; Vannel, Fabien (School of Engineering, Architecture and Landscape (hepia), HES-SO // University of Applied Sciences Western Switzerland) ; Miramond, Benoît (LEAT, Université Cote d'Azur, CNRS, France)

Self-organization is a bio-inspired feature that has been poorly developed when it comes to talking about hardware architectures. Cellular computing approaches have tackled it without considering input data. This paper introduces the SOMA architecture, which proposes an approach for self-organizing machine architectures. In order to achieve the desirable features for such machine, we propose PCSOM, a bio-inspired approach for self-organizing cellular hardware architectures in function of input data. PCSOM is a vector quantization algorithm defined as a network of neurons interconnected through synapses. Synapse pruning makes it possible to organize the cellular system architecture (i.e., topology and configuration of computing elements) in function of the content of input data. We present performance results of the algorithm and we discuss the benefits of PCSOM compared to other existing algorithms.


Keywords:
Conference Type:
full paper
Faculty:
Ingénierie et Architecture
School:
HEPIA - Genève
Institute:
inIT - Institut d'Ingénierie Informatique et des Télécommunications
Publisher:
Ediburgh, UK, 6-9 August 2018
Date:
2018-08
Ediburgh, UK
6-9 August 2018
Pagination:
pp. 272-279
Published in:
Proceedings of 2018 NASA/ESA Conference on Adaptive Hardware and Systems (AHS), 6-9 August 2018, Edinburgh, UK
DOI:
ISBN:
978-1-5386-7753-7
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2020-08-25, last modified 2020-10-27

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)