A change of the prevalent supervised learning techniques is foreseeable in the near future: from the complex, computational expensive algorithms to more flexible and elementary training ones. The strong revitalization of randomized algorithms can be framed in this prospect steering. We recently proposed a model for distributed classification based on randomized neural networks and hyperdimensional computing, which takes into account cost of information exchange between agents using compression. The use of compression is important as it addresses the issues related to the communication bottleneck, however, the original approach is rigid in the way the compression is used. Therefore, in this work, we propose a more flexible approach to compression and compare it to conventional compression algorithms, dimensionality reduction, and quantization techniques.

On effects of compression with hyperdimensional computing in distributed randomized neural networks / Rosato, Antonello; Panella, Massimo; Osipov, Evgeny; Kleyko, Denis. - (2021), pp. 155-167. - LECTURE NOTES IN COMPUTER SCIENCE. [10.1007/978-3-030-85099-9_13].

On effects of compression with hyperdimensional computing in distributed randomized neural networks

Rosato, Antonello;Panella, Massimo
;
2021

Abstract

A change of the prevalent supervised learning techniques is foreseeable in the near future: from the complex, computational expensive algorithms to more flexible and elementary training ones. The strong revitalization of randomized algorithms can be framed in this prospect steering. We recently proposed a model for distributed classification based on randomized neural networks and hyperdimensional computing, which takes into account cost of information exchange between agents using compression. The use of compression is important as it addresses the issues related to the communication bottleneck, however, the original approach is rigid in the way the compression is used. Therefore, in this work, we propose a more flexible approach to compression and compare it to conventional compression algorithms, dimensionality reduction, and quantization techniques.
2021
Advances in Computational Intelligence (LNCS 12862)
978-3-030-85098-2
978-3-030-85099-9
distributed randomized neural networks; compression; vector symbolic architectures; hyperdimensional computing
02 Pubblicazione su volume::02a Capitolo o Articolo
On effects of compression with hyperdimensional computing in distributed randomized neural networks / Rosato, Antonello; Panella, Massimo; Osipov, Evgeny; Kleyko, Denis. - (2021), pp. 155-167. - LECTURE NOTES IN COMPUTER SCIENCE. [10.1007/978-3-030-85099-9_13].
File allegati a questo prodotto
File Dimensione Formato  
Rosato_Effects_2021.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 794.06 kB
Formato Adobe PDF
794.06 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1566163
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact