Regularization of a neural network for binary classification

dc.contributor.advisor	Serrano Moral, Ma. Ángeles (María Ángeles)
dc.contributor.author	Bécares Mas, Andreu
dc.date.accessioned	2019-09-26T16:47:00Z
dc.date.available	2019-09-26T16:47:00Z
dc.date.issued	2019-06
dc.description	Treballs Finals de Grau de Física, Facultat de Física, Universitat de Barcelona, Curs: 2019, Tutora: M. Ángeles Serrano Moral	ca
dc.description.abstract	Neural networks are complex non-linear models used to learn representations of data with multiple levels of abstraction. In this work, we introduce the basic notions of a neural network model, explaining the training process and generalization capabilities. In particular, to avoid overfitting to the training data, we study the L2 regularization method. Finally, an application of 2D vector classification has been developed to illustrate the concepts	ca
dc.format.extent	5 p.
dc.format.mimetype	application/pdf
dc.identifier.uri	https://hdl.handle.net/2445/141012
dc.language.iso	eng	ca
dc.rights	cc-by-nc-nd (c) Bécares, 2019
dc.rights.accessRights	info:eu-repo/semantics/openAccess	ca
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/es/	*
dc.source	Treballs Finals de Grau (TFG) - Física
dc.subject.classification	Xarxes neuronals (Informàtica)	cat
dc.subject.classification	Treballs de fi de grau	cat
dc.subject.other	Neural networks (Computer science)	eng
dc.subject.other	Bachelor's theses	eng
dc.title	Regularization of a neural network for binary classification	eng
dc.type	info:eu-repo/semantics/bachelorThesis	ca

Fitxers

Mostrant 1 - 1 de 1