Multi-objective K-means evolving spiking neural network model based on differential evolution

• Main Authors: Hamed, H. N. A., Saleh, A. Y., Shamsuddin, S. M., Ibrahim, A. O.
• Format: Conference or Workshop Item
• Published: Institute of Electrical and Electronics Engineers Inc. 2016
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.utm.my/id/eprint/73471/; https://www.scopus.com/inward/record.uri?eid=2-s2.0-84965142606&doi=10.1109%2fICCNEEE.2015.7381395&partnerID=40&md5=a9a14ac643ff1ce76bb86e428f54eede
• Institution: Universiti Teknologi Malaysia

In this paper, a multi-objective K-means evolving spiking neural network (MO-KESNN) model based on differential evolution for clustering problems has been presented. K-means has been utilized to improve the ESNN model. This model enhances the flexibility of the ESNN algorithm in producing better solutions which is used to overcome the disadvantages of K-means. Several standard data sets from UCI machine learning are used for evaluating the performance of this model. It has been found that MO-KESNN gives competitive results in clustering accuracy performance and the number of pre-synaptic neurons measure simultaneously compared to the standard K-means. More discussion is provided to prove the effectiveness of the new model in clustering problems. Clustering; Differential Evolution; Evolving Spiking Neural.