eCite Digital Repository

An Extreme Learning Machine Algorithm for Higher Order Neural Network


Xu, S, An Extreme Learning Machine Algorithm for Higher Order Neural Network, Proceedings of the 23rd European Modeling & Simulation Symposium, 12-14 September 2011, Rome, Italy, pp. 418-422. ISBN 978-88-903724-4-5 (2011) [Refereed Conference Paper]

Copyright Statement

Copyright 2011 CAL-TEK S.r.l.

Official URL:


Artificial Neural Networks (ANN) have been widely used as powerful information processing models and adopted in applications such as bankruptcy prediction, predicting costs, forecasting revenue, forecasting share prices and exchange rates, processing documents and many more. This paper uses Extreme Learning Machine (ELM) algorithm for Higher Order Neural Network (HONN) models and applies it in several significant business cases. HONNs are neural networks in which the net input to a computational neuron is a weighted sum of products of its inputs. ELM algorithms randomly choose hidden layer neurons and then only adjust the output weights which connect the hidden layer and the output layer. The experimental results demonstrate that HONN models with ELM algorithm offer significant advantages over standard HONN models as well as traditional ANN models, such as reduced network size, faster training, as well improved simulation and forecasting errors.

Item Details

Item Type:Refereed Conference Paper
Keywords:Higher Order Neural Network, Feedforward Neural Network, Extreme Learning Machine, Financial Forecasting
Research Division:Information and Computing Sciences
Research Group:Machine learning
Research Field:Neural networks
Objective Division:Information and Communication Services
Objective Group:Information systems, technologies and services
Objective Field:Information systems, technologies and services not elsewhere classified
UTAS Author:Xu, S (Dr Shuxiang Xu)
ID Code:74391
Year Published:2011
Deposited By:Information and Communication Technology
Deposited On:2011-11-28
Last Modified:2018-03-27
Downloads:7 View Download Statistics

Repository Staff Only: item control page