Image recognition based on optical reservoir computing
Jiayi Li, Qiang Cai, Pu Li, Yi Yang, K.A. Shore, Yuncai Wang
Abstract
We propose an image recognition approach using a single physical node based optical reservoir computing. Specifically, an optically injected semiconductor laser with self-delayed feedback is used as the reservoir. We perform a handwritten-digit recognition task by greatly increasing the number of virtual nodes in delayed feedback using outputs from multiple delay times. Final simulation results confirm that the recognition accuracy can reach 99% after systematically optimizing the reservoir hyperparameters. Due to its simple architecture, this scheme may provide a resource-efficient alternative approach to image recognition.
Topics & Concepts
Reservoir computingComputer scienceTask (project management)Node (physics)HyperparameterImage (mathematics)Scheme (mathematics)Artificial intelligenceOptical computingPattern recognition (psychology)Electronic engineeringArtificial neural networkEngineeringMathematicsMathematical analysisRecurrent neural networkSystems engineeringStructural engineeringNeural Networks and Reservoir ComputingOptical Network TechnologiesAdvanced Memory and Neural Computing