Spike Sequence Learning in a Photonic Spiking Neural Network Consisting of VCSELs-SA with Supervised Training

• Published in: IEEE journal of selected topics in quantum electronics Vol. 26; no. 5; p. 1
• Main Authors: Song, Ziwei, Xiang, Shuiying, Ren, Zhenxing, Han, Genquan, Hao, Yue
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biological neural networks; Co-design; Design optimization; Encoding; Iterative algorithms; Iterative methods; Learning; Neural networks; Neuromorphics; Neurons; photonic spike-timing-dependent plasticity; Photonic spiking neural network; Photonics; Spikes; Spiking; Supervised learning; supervised spike sequence learning; Training; Vertical cavity surface emission lasers; Vertical cavity surface emitting lasers
• ISSN: 1077-260X; 1558-4542
• DOI: 10.1109/JSTQE.2020.2975564

We propose a fully-connected photonic spiking neural network (SNN) consisting of excitable vertical-cavity surface-emitting lasers with an embedded saturable absorber (VCSELs-SA) to implement spike sequence learning by a supervised training. The photonic spike-timing-dependent plasticity (STDP) is incorporated into a classical remote supervised method (ReSuMe) algorithm to implement supervised training of a photonic SNN for the first time. The computation model of the photonic SNN is derived based on the Yamada model. To optimize the learning process, we further propose a novel measure, the so-called spike sequence distance, to quantitatively evaluate the effects of controllable parameters. The numerical results show that, the photonic SNN successfully reproduce a desirable output spike sequence in response to a spatiotemporal input spike pattern by means of the iteration algorithm to update synaptic weights continuously. These results contribute one step forward toward the device-algorithm co-design and optimization of the all-VCSELs-based energy-efficient photonic SNN.