Experimental reservoir computing with diffractively coupled VCSELs
Moritz Pflüger, Daniel Brunner, Tobias Heuser, James A. Lott, Stephan Reitzenstein, Ingo Fischer
Abstract
We present experiments on reservoir computing (RC) using a network of vertical-cavity surface-emitting lasers (VCSELs) that we diffractively couple via an external cavity. Our optical reservoir computer consists of 24 physical VCSEL nodes. We evaluate the system's memory and solve the 2-bit XOR task and the 3-bit header recognition (HR) task with bit error ratios (BERs) below 1% and the 2-bit digital-to-analog conversion (DAC) task with a root mean square error (RMSE) of 0.067.
Topics & Concepts
OpticsReservoir computingMaterials sciencePhysicsComputer scienceMachine learningRecurrent neural networkArtificial neural networkNeural Networks and Reservoir ComputingOptical Network TechnologiesPhotonic and Optical Devices