Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP

Résumé

Spiking neural networks (SNNs) are good candidates to produce ultra-energy-efficient hardware. However, the performance of these models is currently behind traditional methods. Introducing multi-layered SNNs is a promising way to reduce this gap. We propose in this paper a new threshold adaptation system which uses a timestamp objective at which neurons should fire. We show that our method leads to state-of-the-art classification rates on the MNIST dataset (98.60%) and the Faces/Motorbikes dataset (99.46%) with an unsupervised SNN followed by a linear SVM. We also investigate the sparsity level of the network by testing different inhibition policies and STDP rules.

Dates et versions

hal-02146289 , version 1 (03-06-2019)

Identifiants

Citer

Pierre Falez, Pierre Tirilly, Ioan Marius Bilasco, Philippe Devienne, Pierre Boulet. Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP. International Joint Conference on Neural Networks (IJCNN), Jul 2019, Budapest, Hungary. ⟨hal-02146289⟩
146 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More