Artificial Neural Networks consists of some additives, together with structure and studying set of rules. These additives have an enormous impact at the overall performance of the ANN, however locating top parameters is a hard assignment to attain. An essential requirement for this task is to ensure the reduction of mistakes while inputs and/or hidden neurons are delivered. In practice, it is assumed that this requirement is always actual, but normally its miles fake. In this paper, we propose a new set of rules that guarantees blunders lower when enter variables and/or hidden neurons are delivered to the neural community. The behavior of two traditional algorithms and the proposed algorithm in the forecast of Airline time series had been compared.
Volume 11 | 04-Special Issue
Pages: 2594-2598