File(s) under permanent embargo
Features of higher order neural network with adaptive neurons
One of the most popular machine learning algorithms, ANN (Artificial Neural Network) has been extensively used for Data Mining, which extracts hidden patterns and valuable information from large databases. Data mining has extensive and significant applications in a large variety of areas. This paper introduces a new adaptive Higher Order Neural Network (HONN) model and applies it in data mining tasks such as determining liver disorders and predicting breast cancer recurrences. A new activation function which is a combination of sine and sigmoid functions is used as the neuron activation function for the new HONN model. There are free parameters in the new activation function. The paper compares the new HONN model against a Multi-Layer Perceptron (MLP) with the sigmoid activation function, an RBF Neural Network with the gaussian activation function, and a Recurrent Neural Network (RNN) with the sigmoid activation function. Experimental results show that the new HONN model offers several advantages over conventional ANN models such as improved generalisation capabilities as well as abilities in handling missing values in a dataset.
History
Publication title
Proceeding of the 2nd International Conference on Software Engineering and Data Mining (SEDM2010)Editors
G Kou, Y Peng, F Ko, YW Chen, T TateyamaPagination
484-488ISBN
978-1-4244-7324-3Department/School
School of Information and Communication TechnologyPublisher
IEEE Computer SocietyPlace of publication
Los Alamitos, CAEvent title
Software Engineering and Data Mining (SEDM) International ConferenceEvent Venue
Chengdu, ChinaDate of Event (Start Date)
2010-06-23Date of Event (End Date)
2010-06-25Rights statement
Copyright © 2010 IEEERepository Status
- Restricted