Titre :

Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures

Auteur(s) :

Shahsavari, Mahyar [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Boulet, Pierre [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]

Titre de la revue :

IEEE Transactions on Multi-Scale Computing Systems
Oct.-Dec. 1 2018

Éditeur :

IEEE

Date de publication :

2017-10-09

ISSN :

2332-7766

Mot(s)-clé(s) en anglais :

Neuromorphic Computing
Parameter Evaluations
Spiking Neural Networks
Unsupervised Learning
Memristor

Discipline(s) HAL :

Informatique [cs]/Systèmes embarqués
Informatique [cs]/Architectures Matérielles [cs.AR]
Informatique [cs]/Technologies Émergeantes [cs.ET]
Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]
Informatique [cs]/Réseau de neurones [cs.NE]

Résumé en anglais : [en]

The brain-inspired spiking neural network neuromorphic architecture offers a promising solution for a wide set of cognitive computation tasks at a very low power consumption. Due to the practical feasibility of hardware ...
Lire la suite >The brain-inspired spiking neural network neuromorphic architecture offers a promising solution for a wide set of cognitive computation tasks at a very low power consumption. Due to the practical feasibility of hardware implementation, we present a memristor-based model of hardware spiking neural networks which we simulate with N2S3 (Neural Network Scalable Spiking Simulator), our open source neuromorphic architecture simulator. Although Spiking neural networks are widely used in the community of computational neuroscience and neuromorphic computation, there is still a need for research on the methods to choose the optimum parameters for better recognition efficiency. With the help of our simulator, we analyze and evaluate the impact of different parameters such as number of neurons, STDP window, neuron threshold, distribution of input spikes and memristor model parameters on the MNIST handwritten digit recognition problem. We show that a careful choice of a few parameters (number of neurons, kind of synapse, STDP window and neuron threshold) can significantly improve the recognition rate on this benchmark (around 15 points of improvement for the number of neurons, a few points for the others) with a variability of 4 to 5 points of recognition rate due to the random initialization of the synaptic weights.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL