Files

tfg_da_dalt_severino.pdf (10.66 MB)

Document type

Bachelor thesis

Publication date

2021-01-24

Publication license

cc-by-nc-nd (c) Severino Da Dalt, 2021
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/181290

Adversary detection in neural networks via persistent homology

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

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].

Description

Treballs Finals de Grau de Matemàtiques, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2021, Director: Francisco Belchí Guillamón

Subject

Homologia, Treballs de fi de grau, Xarxes neuronals (Informàtica), Aprenentatge automàtic, Topologia algebraica

Subject (English)

Homology, Bachelor's theses, Neural networks (Computer science), Machine learning, Algebraic topology

Citation

Collections

Treballs Finals de Grau (TFG) - Matemàtiques

Citation

DA DALT, Severino. Adversary detection in neural networks via persistent homology. [consulted: 6 of June of 2026]. Available at: https://hdl.handle.net/2445/181290

Export metadata

JSON - METS

Share record