Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures

Abstract : 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.
Liste complète des métadonnées

Littérature citée [61 références]  Voir  Masquer  Télécharger
Contributeur : Pierre Boulet <>
Soumis le : mercredi 11 octobre 2017 - 17:39:56
Dernière modification le : vendredi 13 octobre 2017 - 01:19:22


Fichiers produits par l'(les) auteur(s)



Mahyar Shahsavari, Pierre Boulet. Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures. IEEE Transactions on Multi-Scale Computing Systems, IEEE, A Paraître, 〈10.1109/TMSCS.2017.2761231〉. 〈hal-01615032〉



Consultations de
la notice


Téléchargements du document