Online spike-based recognition of digits with ultrafast microlaser neurons

• Published in: Frontiers in computational neuroscience Vol. 17; p. 1164472
• Main Authors: Masominia, Amir, Calvet, Laurie E., Thorpe, Simon, Barbay, Sylvain
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 03.07.2023; Frontiers; Frontiers Media S.A
• Subjects: Classification; Classification systems; Computer Science; Energy consumption; Engineering Sciences; Firing pattern; Lasers; microlasers; Neural and Evolutionary Computing; Neural networks; Neurons; Neuroscience; Optics; Ordinary differential equations; Photonic; photonic hardware; Photonics; rank-order code; receptive fields; spiking neurons; temporal coding; receptive fields; microlasers; temporal coding; rank-order code; spiking neurons; photonic hardware
• ISSN: 1662-5188; 1662-5188
• DOI: 10.3389/fncom.2023.1164472

Classification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficiency of such systems. We present numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline computing step. In particular, we discuss the merits of event, spike-time and rank-order based algorithms adapted to this system. These techniques have the potential to significantly improve the efficiency and effectiveness of optical classification systems, minimizing the number of spiking nodes required for a given task and leveraging the parallelism offered by photonic hardware.