Spike pattern recognition using artificial neuron and Spike-Timing-Dependent Plasticity implemented on a multi-core embedded platform

Filippo Grassia (1, 2) , Timothée Levi (1, 3) , E Doukkali (2) , T Kohno (3)

1 IMS - Laboratoire de l'intégration, du matériau au système
2 LTI - Laboratoire des technologies innovantes - UR UPJV 3899
3 IIS - Institute of Industrial Science

The objective of this work is to use a multi-core embedded platform as computing architectures for neural applications relevant to neuromorphic engineering: e.g. robotics, artificial and spiking neural networks. Recently it has been shown how spike-timing-dependent plasticity (STDP) can play a key role in pattern recognition. In particular multiple repeating arbitrary spatiotemporal spike patterns hidden in spike trains can be robustly detected and learned by multiple neurons equipped with spike-timing-dependent plasticity listening to the incoming spike trains. This paper presents an implementation on a biological time scale of STDP algorithm to localize a repeating spatio-temporal spike patterns on a multi-core embedded platform.

Mots clés: Spike-timing-dependent plasticity; spiking neural networks; pattern recognition; neuromorphic engineering

Domaines: Ingénierie biomédicale

Filippo Grassia, Timothée Levi, E Doukkali, T Kohno. Spike pattern recognition using artificial neuron and Spike-Timing-Dependent Plasticity implemented on a multi-core embedded platform. 22th International Symposium on Artificial Life and Robotics, Jan 2017, Beppu, Japan. ⟨hal-01567495⟩