Title :
Nominal-scale Evolving Connectionist Systems
Author :
Watts, Michael J.
Author_Institution :
Lincoln Univ., Canterbury
Abstract :
A method is presented for extending the evolving connectionist system (ECoS) algorithm that allows it to explicitly represent and learn nominal-scale data without the need for an orthogonal or binary encoding scheme. Rigorous evaluation of the algorithm over benchmark data sets shows that it is able to learn, generalise and adapt well to classification problems. The algorithm is potentially useful for data mining tasks.
Keywords :
learning (artificial intelligence); neural nets; binary encoding; data mining; evolving connectionist system algorithm; nominal-scale data; orthogonal encoding; Artificial neural networks; Computational intelligence; Data mining; Decision trees; Encoding; Fuzzy neural networks; Knowledge based systems; Neural networks; Neurons; Training data;
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
DOI :
10.1109/IJCNN.2006.246974
