Proceedings of elm-2017
Éditeur :
Springer Nature Switzerland AG
ISBN :
9783030131821
Date de publication :
10 déc. 2019
Dimensions :
23,5 x 15,5 cm
Langue :
Anglais
Pays d'origine :
Suisse
ELM learning theories show that effective learning algorithms can be derived based on randomly generated hidden neurons (biological neurons, artificial neurons, wavelets, Fourier series,etc) as long as they are nonlinear piecewise continuous, independent of training data and application environments.