Photonic extreme learning machine based on frequency multiplexing
Alessandro Lupo, Lorenz Butschek, Serge Massar
Abstract
The optical domain is a promising field for the physical implementation of neural networks, due to the speed and parallelism of optics. Extreme learning machines (ELMs) are feed-forward neural networks in which only output weights are trained, while internal connections are randomly selected and left untrained. Here we report on a photonic ELM based on a frequency-multiplexed fiber setup. Multiplication by output weights can be performed either offline on a computer or optically by a programmable spectral filter. We present both numerical simulations and experimental results on classification tasks and a nonlinear channel equalization task.
Topics & Concepts
Computer scienceExtreme learning machineMultiplexingPhotonicsArtificial neural networkEqualization (audio)OpticsFilter (signal processing)Multiplication (music)Optical filterElectronic engineeringChannel (broadcasting)Artificial intelligencePhysicsTelecommunicationsAcousticsComputer visionEngineeringNeural Networks and Reservoir ComputingAdvanced Memory and Neural ComputingMachine Learning and ELM