Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204173338> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W3204173338 abstract "This thesis main objective is to study possible applications of the generalisation of persistence theory introduced in [1], [2]. This generalisation extends the notion of persistence to a wider categorical setting, avoiding constructing secondary structures as topological spaces.The first field analysed is graph theory. At first, we studied which classical graph theory invariants could be used as rank function. Another aspect analysed in this thesis is the extension of the study of connectivity in graphs from a persistence viewpoint started in [1] to oriented graphs. Moreover, we studied how different orientation of the same underlying graph can change the distribution of cornerpoints in persistence diagrams, both in deterministic and random graphs.The other application field analysed is image processing. We adapted the notion of steady and ranging sets to the category of sets and used them to define activation and deactivation rules for each pixel. These notions allowed us to define a filter capable of enhancing the signal of pixels close to a border. This filter has proven to be stable under salt and pepper noise perturbation.At last, we used this filter to define a novel pooling layer for convolutional neural networks. In the experimental part, we compared the proposed layer with other state-of-the-art layers. The results show how the proposed layer outperform the other layers in term of accuracy. Moreover, by concatenating the proposed and the Max pooling, it is possible to improve accuracy further.[1] Bergomi, M.G., Ferri, M., Vertechi, P., Zuffi, L. (2020), Beyond topological persistence: Starting from networks, arXiv.[2] Bergomi, M. G., & Vertechi, P. (2020). Rank-based persistence. Theory and Applications of Categories, 35, 228-260." @default.
- W3204173338 created "2021-10-11" @default.
- W3204173338 creator A5035910047 @default.
- W3204173338 date "2021-05-20" @default.
- W3204173338 modified "2023-10-16" @default.
- W3204173338 title "Non-topological persistence for data analysis and machine learning" @default.
- W3204173338 doi "https://doi.org/10.48676/unibo/amsdottorato/9809" @default.
- W3204173338 hasPublicationYear "2021" @default.
- W3204173338 type Work @default.
- W3204173338 sameAs 3204173338 @default.
- W3204173338 citedByCount "0" @default.
- W3204173338 crossrefType "dissertation" @default.
- W3204173338 hasAuthorship W3204173338A5035910047 @default.
- W3204173338 hasConcept C106131492 @default.
- W3204173338 hasConcept C11413529 @default.
- W3204173338 hasConcept C114614502 @default.
- W3204173338 hasConcept C119857082 @default.
- W3204173338 hasConcept C153180895 @default.
- W3204173338 hasConcept C154945302 @default.
- W3204173338 hasConcept C184720557 @default.
- W3204173338 hasConcept C31972630 @default.
- W3204173338 hasConcept C33923547 @default.
- W3204173338 hasConcept C41008148 @default.
- W3204173338 hasConcept C5274069 @default.
- W3204173338 hasConcept C70437156 @default.
- W3204173338 hasConcept C80444323 @default.
- W3204173338 hasConceptScore W3204173338C106131492 @default.
- W3204173338 hasConceptScore W3204173338C11413529 @default.
- W3204173338 hasConceptScore W3204173338C114614502 @default.
- W3204173338 hasConceptScore W3204173338C119857082 @default.
- W3204173338 hasConceptScore W3204173338C153180895 @default.
- W3204173338 hasConceptScore W3204173338C154945302 @default.
- W3204173338 hasConceptScore W3204173338C184720557 @default.
- W3204173338 hasConceptScore W3204173338C31972630 @default.
- W3204173338 hasConceptScore W3204173338C33923547 @default.
- W3204173338 hasConceptScore W3204173338C41008148 @default.
- W3204173338 hasConceptScore W3204173338C5274069 @default.
- W3204173338 hasConceptScore W3204173338C70437156 @default.
- W3204173338 hasConceptScore W3204173338C80444323 @default.
- W3204173338 hasLocation W32041733381 @default.
- W3204173338 hasOpenAccess W3204173338 @default.
- W3204173338 hasPrimaryLocation W32041733381 @default.
- W3204173338 hasRelatedWork W1503984136 @default.
- W3204173338 hasRelatedWork W1512172501 @default.
- W3204173338 hasRelatedWork W1567165723 @default.
- W3204173338 hasRelatedWork W1659060676 @default.
- W3204173338 hasRelatedWork W2003212196 @default.
- W3204173338 hasRelatedWork W2098620241 @default.
- W3204173338 hasRelatedWork W2100422476 @default.
- W3204173338 hasRelatedWork W2161612408 @default.
- W3204173338 hasRelatedWork W2599394021 @default.
- W3204173338 hasRelatedWork W2745722324 @default.
- W3204173338 hasRelatedWork W2752264644 @default.
- W3204173338 hasRelatedWork W2951046113 @default.
- W3204173338 hasRelatedWork W2952771348 @default.
- W3204173338 hasRelatedWork W2962875400 @default.
- W3204173338 hasRelatedWork W2981151966 @default.
- W3204173338 hasRelatedWork W2991962490 @default.
- W3204173338 hasRelatedWork W3011426723 @default.
- W3204173338 hasRelatedWork W3048947240 @default.
- W3204173338 hasRelatedWork W3141260085 @default.
- W3204173338 hasRelatedWork W3165237112 @default.
- W3204173338 isParatext "false" @default.
- W3204173338 isRetracted "false" @default.
- W3204173338 magId "3204173338" @default.
- W3204173338 workType "dissertation" @default.