Identification of a specific limitation on local-feedback recurrent networks acting as Mealy-Moore machines

This paper describes a proof which identifies limitations of local-feedback recurrent networks (LFRN's) in representing Mealy-Moore machines. Specifically, it identifies a class of machines that are unrepresentable in these networks. While it is known that LFRN's cannot represent all automata, this is the first paper to show a specific class of unrepresentable automata. The paper goes beyond previous work in the area by addressing realistic activation functions, arbitrary network architectures, and more general computing machines.