Excitatory and Inhibitory Memristive Synapses for Spiking Neural Networks

Abstract : Neuromorphic chips are composed of silicon neurons, synapses and memories for synaptic weight. Moreover we can find a fourth part dedicated to synaptic plasticity algorithm. Even though we can find some low-power silicon neurons, the power consumption reduction of synapses, memories and plasticity algorithm is not enough explored. Since memristor coming-out in 2008, neuromorphic designers investigate the possibility of using memristors as plastic synapses due to their intrinsic property of plasticity. This nanocomponent gathers the function of synapse, the weight storage and the plasticity. So far, the proposed solutions cannot manage both excitatory and inhibitory memristive synapses with one single design. In this paper we will present an elegant solution based on current conveyor (CCII) fordriving memristor as excitatory or inhibitory synapses following the neural network implementation.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00975440
Contributor : Sylvain Saighi <>
Submitted on : Tuesday, April 8, 2014 - 4:17:59 PM
Last modification on : Thursday, January 11, 2018 - 6:21:08 AM

Identifiers

Citation

Gwendal Lecerf, Jean Tomas, Sylvain Saïghi. Excitatory and Inhibitory Memristive Synapses for Spiking Neural Networks. IEEE International Symposium on Circuits and Systems, May 2013, China. ⟨10.1109/ISCAS.2013.6572171⟩. ⟨hal-00975440⟩

Share

Metrics

Record views

85