Matches in SemOpenAlex for { <https://semopenalex.org/work/W3009906898> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W3009906898 abstract "In recent years, Deep Learning techniques have swept the state-of-the-art of many applications of Machine Learning, becoming the new standard approach for them. The architectures issued from these techniques have been used for transfer learning, which extended the power of deep models to tasks that did not have enough data to fully train them from scratch. This thesis' subject of study is the representation spaces created by deep architectures. First, we study properties inherent to them, with particular interest in dimensionality redundancy and precision of their features. Our findings reveal a strong degree of robustness, pointing the path to simple and powerful compression schemes. Then, we focus on refining these representations. We choose to adopt a cross-modal multi-task problem, and design a loss function capable of taking advantage of data coming from multiple modalities, while also taking into account different tasks associated to the same dataset. In order to correctly balance these losses, we also we develop a new sampling scheme that only takes into account examples contributing to the learning phase, i.e. those having a positive loss. Finally, we test our approach in a large-scale dataset of cooking recipes and associated pictures. Our method achieves a 5-fold improvement over the state-of-the-art, and we show that the multi-task aspect of our approach promotes a semantically meaningful organization of the representation space, allowing it to perform subtasks never seen during training, like ingredient exclusion and selection. The results we present in this thesis open many possibilities, including feature compression for remote applications, robust multi-modal and multi-task learning, and feature space refinement. For the cooking application, in particular, many of our findings are directly applicable in a real-world context, especially for the detection of allergens, finding alternative recipes due to dietary restrictions, and menu planning." @default.
- W3009906898 created "2020-03-13" @default.
- W3009906898 creator A5054009139 @default.
- W3009906898 date "2018-12-11" @default.
- W3009906898 modified "2023-09-23" @default.
- W3009906898 title "Deep representation spaces" @default.
- W3009906898 hasPublicationYear "2018" @default.
- W3009906898 type Work @default.
- W3009906898 sameAs 3009906898 @default.
- W3009906898 citedByCount "0" @default.
- W3009906898 crossrefType "dissertation" @default.
- W3009906898 hasAuthorship W3009906898A5054009139 @default.
- W3009906898 hasConcept C104317684 @default.
- W3009906898 hasConcept C108583219 @default.
- W3009906898 hasConcept C111919701 @default.
- W3009906898 hasConcept C119857082 @default.
- W3009906898 hasConcept C152124472 @default.
- W3009906898 hasConcept C154945302 @default.
- W3009906898 hasConcept C17744445 @default.
- W3009906898 hasConcept C185592680 @default.
- W3009906898 hasConcept C199539241 @default.
- W3009906898 hasConcept C2776359362 @default.
- W3009906898 hasConcept C41008148 @default.
- W3009906898 hasConcept C55493867 @default.
- W3009906898 hasConcept C59404180 @default.
- W3009906898 hasConcept C63479239 @default.
- W3009906898 hasConcept C94625758 @default.
- W3009906898 hasConceptScore W3009906898C104317684 @default.
- W3009906898 hasConceptScore W3009906898C108583219 @default.
- W3009906898 hasConceptScore W3009906898C111919701 @default.
- W3009906898 hasConceptScore W3009906898C119857082 @default.
- W3009906898 hasConceptScore W3009906898C152124472 @default.
- W3009906898 hasConceptScore W3009906898C154945302 @default.
- W3009906898 hasConceptScore W3009906898C17744445 @default.
- W3009906898 hasConceptScore W3009906898C185592680 @default.
- W3009906898 hasConceptScore W3009906898C199539241 @default.
- W3009906898 hasConceptScore W3009906898C2776359362 @default.
- W3009906898 hasConceptScore W3009906898C41008148 @default.
- W3009906898 hasConceptScore W3009906898C55493867 @default.
- W3009906898 hasConceptScore W3009906898C59404180 @default.
- W3009906898 hasConceptScore W3009906898C63479239 @default.
- W3009906898 hasConceptScore W3009906898C94625758 @default.
- W3009906898 hasOpenAccess W3009906898 @default.
- W3009906898 hasRelatedWork W2023414700 @default.
- W3009906898 hasRelatedWork W2164700406 @default.
- W3009906898 hasRelatedWork W2184503290 @default.
- W3009906898 hasRelatedWork W2224525916 @default.
- W3009906898 hasRelatedWork W2248206634 @default.
- W3009906898 hasRelatedWork W2260846929 @default.
- W3009906898 hasRelatedWork W2294805292 @default.
- W3009906898 hasRelatedWork W2402540331 @default.
- W3009906898 hasRelatedWork W2412879760 @default.
- W3009906898 hasRelatedWork W2613634265 @default.
- W3009906898 hasRelatedWork W2806695138 @default.
- W3009906898 hasRelatedWork W2899998199 @default.
- W3009906898 hasRelatedWork W2904036825 @default.
- W3009906898 hasRelatedWork W2951657494 @default.
- W3009906898 hasRelatedWork W2999255011 @default.
- W3009906898 hasRelatedWork W3002701914 @default.
- W3009906898 hasRelatedWork W3025504802 @default.
- W3009906898 hasRelatedWork W3035980362 @default.
- W3009906898 hasRelatedWork W3087641101 @default.
- W3009906898 hasRelatedWork W3152651027 @default.
- W3009906898 isParatext "false" @default.
- W3009906898 isRetracted "false" @default.
- W3009906898 magId "3009906898" @default.
- W3009906898 workType "dissertation" @default.