Economic Dispatch (ED) problems have recently been solved by artificial neural network approaches. In most of these dispatch models the transmission system representation is totally neglected. Therefore, such procedures may calculate dispatch policies that do not take into account important active power constraints. Another drawback pointed out in the literature is that some of these neural approaches fail to converge efficiently toward feasible equilibrium points. This paper discusses the application of a modified Hopfield architecture for solving an ED problem with transmission system representation. The transmission system is represented through linear load flow equations and constraints on active power flows. Simulation results and a sensitivity analysis involving IEEE 14-bus test system are presented to illustrate efficiency of the proposed approach.