An improvement of extreme learning machine using subclass clustering

Simple item page
dc.contributor.authorWatchareeruetai, Ukrit
dc.contributor.authorJiramaneepinit, Boonnithi
dc.date.accessioned2026-08-06T10:20:26Z
dc.date.available2026-08-06T10:20:26Z
dc.date.issued2018-07-02
dc.description.abstractExtreme learning machine (ELM) is an extremely fast learning algorithm proposed for a single-hidden-layer feed-forward neural network (SLFN). ELM projects a set of training instances into a random feature space, and then analytically calculates the weight matrix connecting between the hidden layer and the output layer, leading to a very fast learning speed. This paper proposes an improved version of ELM, named clustering-ELM, that assigns a subclass to each training instances and learns for a weight matrix that projects random features into subclass. In the prediction step, the responses from output nodes of the same class are integrated into one using maximum function. Experimental results conducted on various benchmark datasets reveal a promising performance of the proposed clustering-ELM, compared to the standard ELM.
dc.identifier.citation2018 22nd International Computer Science and Engineering Conference Icsec 2018, 2018
dc.identifier.doi10.1109/ICSEC.2018.8712758
dc.identifier.other2-s2.0-85066498117
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/8703
dc.source2018 22nd International Computer Science and Engineering Conference Icsec 2018
dc.subjectClustering
dc.subjectExtreme learning machine
dc.subjectK-means algorithm
dc.subjectSingle hidden-layer feedforward neural network
dc.subjectSubclass
dc.titleAn improvement of extreme learning machine using subclass clustering
dc.typeConference Paper

Files

Collections

Research