An Extreme Learning Machine Algorithm for Higher Order Neural Network

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.