Adversary detection in neural networks via persistent homology

dc.contributor.advisor	Belchí Guillamón, Francisco
dc.contributor.author	Da Dalt, Severino
dc.date.accessioned	2021-11-16T12:34:02Z
dc.date.available	2021-11-16T12:34:02Z
dc.date.issued	2021-01-24
dc.description	Treballs Finals de Grau de Matemàtiques, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2021, Director: Francisco Belchí Guillamón	ca
dc.description.abstract	[en] The main goal of this work is to present a recently-invented homology theory called persistent homology and its application on the detection of adversary examples of neural network presented in the paper [4].	ca
dc.format.extent	35 p.
dc.format.mimetype	application/pdf
dc.identifier.uri	https://hdl.handle.net/2445/181290
dc.language.iso	eng	ca
dc.rights	cc-by-nc-nd (c) Severino Da Dalt, 2021
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) - Matemàtiques
dc.subject.classification	Homologia	ca
dc.subject.classification	Treballs de fi de grau
dc.subject.classification	Xarxes neuronals (Informàtica)	ca
dc.subject.classification	Aprenentatge automàtic	ca
dc.subject.classification	Topologia algebraica	ca
dc.subject.other	Homology	en
dc.subject.other	Bachelor's theses
dc.subject.other	Neural networks (Computer science)	en
dc.subject.other	Machine learning	en
dc.subject.other	Algebraic topology	en
dc.title	Adversary detection in neural networks via persistent homology	ca
dc.type	info:eu-repo/semantics/bachelorThesis	ca

Fitxers

Mostrant 1 - 1 de 1