Echo State Networks-based Reservoir Computing for MNIST Handwritten Digits Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Echo State Networks-based Reservoir Computing for MNIST Handwritten Digits Recognition

Résumé

Reservoir Computing is an attractive paradigm of recurrent neural network architecture, due to the ease of training and existing neuromorphic implementations. Successively applied on speech recognition and time series forecasting, few works have so far studied the behavior of such networks on computer vision tasks. Therefore we decided to investigate the ability of Echo State Networks to classify the digits of the MNIST database. We show that even if ESNs are not able to outperform state-of-the-art convolutional networks, they allow low error thanks to a suitable preprocessing of images. The best performance is obtained with a large reservoir of 4,000 neurons, but committees of smaller reservoirs are also appealing and might be further investigated.
Fichier principal
Vignette du fichier
7114d7f9-5909-43d4-aa1f-257aa4604217-author.pdf (1.53 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02131170 , version 1 (16-05-2019)

Identifiants

  • HAL Id : hal-02131170 , version 1

Citer

Nils Schaetti, Michel Salomon, Raphael Couturier. Echo State Networks-based Reservoir Computing for MNIST Handwritten Digits Recognition. International Conference on Computational Science and Engineering, Aug 2016, Paris, France. ⟨hal-02131170⟩
129 Consultations
1719 Téléchargements

Partager

Gmail Facebook X LinkedIn More