The application of ridge polynomial neural network to multi-step ahead financial time series prediction

Motivated by the slow learning properties of multilayer perceptrons (MLPs) which utilize computationally intensive training algorithms, such as the backpropagation learning algorithm, and can get trapped in local minima, this work deals with ridge polynomial neural networks (RPNN), which maintain fast learning properties and powerful mapping capabilities of single layer high order neural networks. The RPNN is constructed from a number of increasing orders of Pi

• Type: Journal
• Year: 2008
• Where: NCA
• Authors: Rozaida Ghazali, Abir Jaafar Hussain, Panos Liatsis, H. Tawfik
• Keywords: Computer Networks, NCA 2008, Neural Networks, Order Neural Networks, Polynomial Neural Networks