On the Use of Quasi-Newton-Based Training of a Feedforward Neural Network for Time Series Forecasting

This paper examines the e ectiveness of using a quasi-Newton based training of a feedforward neural network for forecasting. We have developed a novel quasi-Newton based training algorithm using a generalized logistic function. We have shown that a well designed feed forward structure can lead to a good forecast without the use of the more complicated feedback/feedforward structure of the recurrent network. keywords: Feed forward neural network, quasi-Newton, forecasting