ISBN-13: 9783659358746 / Angielski / Miękka / 2013 / 172 str.
Selection of the topology of a neural network and correct parameters for the learning algorithm is a tedious task for designing an optimal artificial neural network, which is smaller, faster and with a better generalization performance. This book is my effort to mainly showcase the capability of time series prediction using neural network approach to predict complex Nonlinear datasets for forecasting. Experiments were carried out on Netflow series. It is observed that these problems exhibit a rich chaotic behavior and also leads to strange attractor. Multi-step ahead predictions have been carried out and the proposed neural network models have been optimized.
Selection of the topology of a neural network and correct parameters for the learning algorithm is a tedious task for designing an optimal artificial neural network, which is smaller, faster and with a better generalization performance. This book is my effort to mainly showcase the capability of time series prediction using neural network approach to predict complex Nonlinear datasets for forecasting. Experiments were carried out on Netflow series. It is observed that these problems exhibit a rich chaotic behavior and also leads to strange attractor. Multi-step ahead predictions have been carried out and the proposed neural network models have been optimized.