Nominal-scale Evolving Connectionist Systems

— 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.

• Type: Conference
• Year: 2006
• Where: IJCNN
• Authors: Michael J. Watts
• Keywords: Algorithm, Benchmark Data Sets, Binary Encoding Scheme, IJCNN 2006