Impact of Increasing Number of Neurons on Performance of Neuromorphic Architecture

Abstract : Pattern recognition is used to classify the input data into different classes based on extracted key features. Increasing the recognition rate of pattern recognition applications is a challenging task. The spike neural networks inspired from physiological brain architecture, is a neuromorphic hardware implementation of network of neurons. A sample of neuromor-phic architecture has two layers of neurons, input and output. The number of input neurons is fixed based on the input data patterns. While the number of outputs neurons can be different. The goal of this paper is performance evaluation of neuromorphic architecture in terms of recognition rates using different numbers of output neurons. For this purpose a simulation environment of N2S3 and MNIST handwritten digits are used. Our simulation results show the recognition rate for various number of output neurons, 20, 30, 50, 100, 200, and 300 is 70%, 74%, 79%, 85%, 89%, and 91%, respectively.
Type de document :
Communication dans un congrès
CADS 2017 - 19th CSI International Symposium on Computer Architecture & Digital Systems, Dec 2017, Kish, Iran
Liste complète des métadonnées

Littérature citée [47 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01633418
Contributeur : Mahyar Shahsavari <>
Soumis le : dimanche 12 novembre 2017 - 23:59:06
Dernière modification le : samedi 18 novembre 2017 - 18:16:02

Fichiers

Sub61_shahsavari_CADS17.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01633418, version 1

Citation

Mahyar Shahsavari, Pierre Boulet, Asadollah Shahbahrami, Said Hamdioui. Impact of Increasing Number of Neurons on Performance of Neuromorphic Architecture. CADS 2017 - 19th CSI International Symposium on Computer Architecture & Digital Systems, Dec 2017, Kish, Iran. 〈hal-01633418〉

Partager

Métriques

Consultations de la notice

20

Téléchargements de fichiers

30