DocumentCode :
1636532
Title :
Towards integrated optical spiking neural networks: Delaying spikes on chip
Author :
Van Vaerenbergh, Thomas ; Fiers, Martin ; Bienstman, Peter ; Dambre, Joni
Author_Institution :
Dept. of Inf. Technol., Ghent Univ. - imec, Ghent, Belgium
fYear :
2013
Firstpage :
1
Lastpage :
2
Abstract :
To emulate Spiking Neural Networks (SNN) on an integrated photonic chip, one needs both excitable optical components, to mimic the spiking neurons, and delay lines acting as the connections that transfer the pulses between those neurons. Such an optical connection needs to have a delay in the order of magnitude of the internal timescale of the neuron. Recently, we showed how passive silicon-on-insulator microring resonators can be used as an all-optical spiking neuron. In this paper, we investigate how the dynamics of the microring can be used to obtain a meaningful spike delay. The possibility to delay spikes on chip paves the way towards fully integrated optical SNNs.
Keywords :
integrated optics; micro-optics; micromechanical resonators; optical delay lines; optical interconnections; optical neural nets; optical resonators; silicon-on-insulator; all-optical spiking neuron; delay lines; delay spikes; excitable optical component; integrated optical spiking neural networks; integrated photonic chip; internal timescale; meaningful spike delay; microring dynamics; optical connection; passive silicon-on-insulator microring resonators; pulse transfer; spike on chip delaying; Delays; Laser excitation; Neurons; Nonlinear optics; Optical pulses; Optical resonators; Optical waveguides;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Laser Dynamics and Nonlinear Photonics, 2013 Sixth "Rio De La Plata" Workshop on
Conference_Location :
Montevideo
Type :
conf
DOI :
10.1109/LDNP.2013.6777418
Filename :
6777418
Link To Document :
بازگشت