BECERRA ALONSO, DAVID, CARBONERO RUZ, MARIANO, MARTÍNEZ ESTUDILLO, ALFONSO CARLOS, MARTÍNEZ ESTUDILLO, FRANCISCO JOSÉ

No

Adapt. Learn. Optim.

Article

Científica

✗

✗

0.145

https://www.scopus.com/inward/record.uri?eid=2-s2.0-84959210968&doi=10.1007%2f978-3-319-04741-6_1&partnerID=40&md5=c1a23d76257320e9ee87cc6c130a1cc2

01/01/2014

2-s2.0-84959210968

10.1007/978-3-319-04741-6_1

The Extreme Learning Machine classifier is used to perform the perturbative method known as Sensitivity Analysis. The method returns a measure of class sensitivity per attribute. The results show a strong consistency for classifiers with different random input weights. In order to present the results obtained in an intuitive way, two forms of representation are proposed and contrasted against each other. The relevance of both attributes and classes is discussed. Class stability and the ease with which a pattern can be correctly classified are inferred from the results. The method can be used with any classifier that can be replicated with different random seeds. © Springer International Publishing Switzerland 2014.

Classification; Elm feature space; Elm solutions space; Extreme learning machine; Sensitivity analysis; Stochastic classifiers

• DAVID BECERRA ALONSO
• MARIANO CARBONERO RUZ
• ALFONSO CARLOS MARTÍNEZ ESTUDILLO
• FRANCISCO JOSÉ MARTÍNEZ ESTUDILLO