Receptive Field-Based All-Optical Spiking Neural Network for Image Processing
- 19 October 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Quantum Electronics
- Vol. 60 (1) , 1-11
Abstract
We report on a novel structure of a receptive field (RF)-based multi-layer all-optical neural network using a micropillar laser with a saturable absorber (SA) for image processing. From the perspective of biological vision, the realization of image processing based on the RF provides the biological rationality for the machine vision implemented by the spiking neural network (SNN). By exploiting the fast physical mechanisms of gain and absorption in the SA laser, the photonic spike-timing-dependent plasticity (STDP) curves are achieved to train the weights. Here, the source image pixels are mapped into the temporal information of spike trains injected into the neural network through the temporal coding method called time-to-first-spike encoding. Different source images are processed and tested by the proposed photonic SNN. Simulation results show that our proposed system can process not only simple binary images but also complex color images under the adjustment of STDP rules. When considering the robustness, we demonstrate the tolerance of the image segmentation to the time jitter. These results indicate that our proposed photonic SNN can achieve high-resolution processing of complex source images. Additionally, the time-multiplexing technique can be further adopted to simplify the RF structure, which is expected to reduce the complexity of the whole system, thus facilitating physical applications. Our work offers the prospect for a high-speed photonic spiking platform for image processing.Keywords
Funding Information
- National Key Research and Development Program of China (2021YFB2801900, 2021YFB2801901, 2021YFB2801902, 2021YFB2801904)
- National Natural Science Foundation of China (62004135, 62001317, 62171305, 62111530301)
- Natural Science Research Project of Jiangsu Higher Education Institutions of China (20KJA416001)
- Natural Science Foundation of Jiangsu Province (BK20200855)
- Belarusian Republican Foundation for Fundamental Research (F22KI-020)
This publication has 72 references indexed in Scilit:
- Investigation of vertical cavity surface emitting laser dynamics for neuromorphic photonic systemsApplied Physics Letters, 2012
- Solitary and coupled semiconductor ring lasers as optical spiking neuronsPhysical Review E, 2011
- Optical injection in semiconductor ring lasersPhysical Review A, 2010
- Fast Thermo-Optical Excitability in a Two-Dimensional Photonic CrystalPhysical Review Letters, 2006
- All-optical bistable band-edge Bloch modes in a two-dimensional photonic crystalApplied Physics Letters, 2006
- Contour detection based on nonclassical receptive field inhibitionIEEE Transactions on Image Processing, 2003
- Spike-timing-dependent synaptic modification induced by natural spike trainsNature, 2002
- Synaptic Modification by Correlated Activity: Hebb's Postulate RevisitedAnnual Review of Neuroscience, 2001
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997
- A theoretical analysis of self-sustained pulsation phenomena in narrow-stripe semiconductor lasersIEEE Journal of Quantum Electronics, 1993