Unsupervised features extraction from asynchronous silicon retina through Spike-Timing-Dependent Plasticity
Résumé
—In this paper, we present a novel approach to extract complex and overlapping temporally correlated features directly from spike-based dynamic vision sensors. A spiking neural network capable of performing multilayer unsuper-vised learning through Spike-Timing-Dependent Plasticity is introduced. It shows exceptional performances at detecting cars passing on a freeway recorded with a dynamic vision sensor, after only 10 minutes of fully unsupervised learning. Our methodology is thoroughly explained and first applied to a simpler example of ball trajectory learning. Two unsuper-vised learning strategies are investigated for advanced features learning. Robustness of our network to synaptic and neuron variability is assessed and virtual immunity to noise and jitter is demonstrated.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...