Selection of the most "efficient" Reed-Solomon code for a specific application using neural networks

Reed-Solomon (RS) codes have found a widespread applications in digital communications and digital recording systems in the past two decades. The catalog of Reed-Solomon is a rather long one. To select a proper code for a given application, the system designer is compelled to deal with numerous tables, graphs and equations. We introduce a novel application of artificial neural networks (NN) in selecting the most "efficient" RS code for a specific design scenario. It is shown that 98.04% of the time the NN makes correct selections.