Experimental Demonstration of Optoelectronic Equalization for Short-reach Transmission with Reservoir Computing
This addresses signal degradation in optical communication systems, but it is incremental as it applies an existing machine learning method (reservoir computing) to a specific domain.
The paper tackled the problem of short-reach optical transmission by experimentally demonstrating a receiver that uses reservoir computing to equalize a 32 GBd OOK signal over up to 80 km of SMF, achieving equalization of up to 4 spectral slices.
A receiver with shared complexity between optical and digital domains is experimentally demonstrated. Reservoir computing is used to equalize up to 4 directly-detected optically filtered spectral slices of a 32 GBd OOK signal over up to 80 km of SMF.