Title A Preliminary Study of Diversity in Extreme Learning Machines Ensembles
Authors PERALES GONZÁLEZ, CARLOS, CARBONERO RUZ, MARIANO, BECERRA ALONSO, DAVID, FERNÁNDEZ NAVARRO, FRANCISCO DE ASÍS
External publication No
Means Lect. Notes Comput. Sci.
Scope Proceedings Paper
Nature Científica
JCR Quartile 4
SJR Quartile 2
SJR Impact 0.283
Web https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048895231&doi=10.1007%2f978-3-319-92639-1_25&partnerID=40&md5=4eae5c44e664b66d50a7600b3e8b2061
Publication date 01/01/2018
ISI 000443487900025
Scopus Id 2-s2.0-85048895231
DOI 10.1007/978-3-319-92639-1_25
Abstract In this paper, the neural network version of Extreme Learning Machine (ELM) is used as a base learner for an ensemble meta algorithm which promotes diversity explicitly in the ELM loss function. The cost function proposed encourages orthogonality (scalar product) in the parameter space. Other ensemble-based meta-algorithms from AdaBoost family are used for comparison purposes. Both accuracy and diversity presented in our proposal are competitive, thus reinforcing the idea of introducing diversity explicitly.
Keywords Extreme learning machine; Diversity; Machine learning; Ensemble; AdaBoost
Universidad Loyola members

Change your preferences Manage cookies