FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202192845> ?p ?o ?g. }

• W3202192845 abstract "Machine Learning (ML) and Artificial Intelligence (AI) are more present than ever in our society's collective discourse. CEOs, politicians, and fellow citizens all put incredibly high hopes and expectations into AI's future capabilities. In many applications, ranging from the medical field to autonomous robots such as self-driving cars, we are starting to entrust human lives to decisions made by algorithms and machines. With credit scoring algorithms and hiring practices now adopting these new technologies, machine learning can have a profound impact on people’s lives. The expectation of inherent fairness, accuracy, and consistency we have of these algorithms goes beyond even what we expect from fellow humans. Indeed, these expectations are driven by the desire to improve everyone’s quality of life. Many current machine learning models focus on providing the highest possible accuracy. However, these models are often black boxes that are hard to examine. They are mostly discriminative models that focus on modeling decisions based on the training data, but do not create a model for the data itself. This is important, as we are interested in questioning the training data to detect systematic biases. Furthermore, we are also highly interested in asking the model whether the current data it is processing fits the training data. In other words, is it qualified to make decisions and knows what it is talking about, or whether it simply does not know. Therefore, we require a generative model that can answer these, and other, questions. In this thesis, we focus on deep generative models based on probabilistic circuits; a family of statistical models that allows us to answer a wide range of normalized probability queries with guarantees on computational time. We can then ask these generative models about biases, including how confident they are about a particular answer, as they know when they do not know. We develop models for count data, extend them to non-parametric models, and models based on dictionaries of distributions. They cover a large variety of use-cases. We then make connections to Deep Neural Networks and show how to build generative models from them with inference guarantees. All these models cover a wide range of use cases, including hybrid domains. Moreover, we present a model that learns from the data making most decisions automatically so that non-experts can also benefit from these powerful tools. This will contribute to the democratization of machine learning." @default.
• W3202192845 created "2021-10-11" @default.
• W3202192845 creator A5085989495 @default.
• W3202192845 date "2021-01-01" @default.
• W3202192845 modified "2023-09-24" @default.
• W3202192845 title "Deep Networks That Know When They Don't Know" @default.
• W3202192845 doi "https://doi.org/10.26083/tuprints-00018525" @default.
• W3202192845 hasPublicationYear "2021" @default.
• W3202192845 type Work @default.
• W3202192845 sameAs 3202192845 @default.
• W3202192845 citedByCount "0" @default.
• W3202192845 crossrefType "dissertation" @default.
• W3202192845 hasAuthorship W3202192845A5085989495 @default.
• W3202192845 hasConcept C108583219 @default.
• W3202192845 hasConcept C111472728 @default.
• W3202192845 hasConcept C119857082 @default.
• W3202192845 hasConcept C120665830 @default.
• W3202192845 hasConcept C121332964 @default.
• W3202192845 hasConcept C124101348 @default.
• W3202192845 hasConcept C138885662 @default.
• W3202192845 hasConcept C154945302 @default.
• W3202192845 hasConcept C167966045 @default.
• W3202192845 hasConcept C192209626 @default.
• W3202192845 hasConcept C202444582 @default.
• W3202192845 hasConcept C2522767166 @default.
• W3202192845 hasConcept C2776436953 @default.
• W3202192845 hasConcept C2778519782 @default.
• W3202192845 hasConcept C2779530757 @default.
• W3202192845 hasConcept C33923547 @default.
• W3202192845 hasConcept C38652104 @default.
• W3202192845 hasConcept C39890363 @default.
• W3202192845 hasConcept C41008148 @default.
• W3202192845 hasConcept C75684735 @default.
• W3202192845 hasConcept C9652623 @default.
• W3202192845 hasConceptScore W3202192845C108583219 @default.
• W3202192845 hasConceptScore W3202192845C111472728 @default.
• W3202192845 hasConceptScore W3202192845C119857082 @default.
• W3202192845 hasConceptScore W3202192845C120665830 @default.
• W3202192845 hasConceptScore W3202192845C121332964 @default.
• W3202192845 hasConceptScore W3202192845C124101348 @default.
• W3202192845 hasConceptScore W3202192845C138885662 @default.
• W3202192845 hasConceptScore W3202192845C154945302 @default.
• W3202192845 hasConceptScore W3202192845C167966045 @default.
• W3202192845 hasConceptScore W3202192845C192209626 @default.
• W3202192845 hasConceptScore W3202192845C202444582 @default.
• W3202192845 hasConceptScore W3202192845C2522767166 @default.
• W3202192845 hasConceptScore W3202192845C2776436953 @default.
• W3202192845 hasConceptScore W3202192845C2778519782 @default.
• W3202192845 hasConceptScore W3202192845C2779530757 @default.
• W3202192845 hasConceptScore W3202192845C33923547 @default.
• W3202192845 hasConceptScore W3202192845C38652104 @default.
• W3202192845 hasConceptScore W3202192845C39890363 @default.
• W3202192845 hasConceptScore W3202192845C41008148 @default.
• W3202192845 hasConceptScore W3202192845C75684735 @default.
• W3202192845 hasConceptScore W3202192845C9652623 @default.
• W3202192845 hasLocation W32021928451 @default.
• W3202192845 hasOpenAccess W3202192845 @default.
• W3202192845 hasPrimaryLocation W32021928451 @default.
• W3202192845 hasRelatedWork W10853339 @default.
• W3202192845 hasRelatedWork W1554130038 @default.
• W3202192845 hasRelatedWork W1840126875 @default.
• W3202192845 hasRelatedWork W2025110618 @default.
• W3202192845 hasRelatedWork W2407760288 @default.
• W3202192845 hasRelatedWork W2407855925 @default.
• W3202192845 hasRelatedWork W2564426127 @default.
• W3202192845 hasRelatedWork W2573721624 @default.
• W3202192845 hasRelatedWork W2625014243 @default.
• W3202192845 hasRelatedWork W2767361718 @default.
• W3202192845 hasRelatedWork W2778796877 @default.
• W3202192845 hasRelatedWork W2889715237 @default.
• W3202192845 hasRelatedWork W2947364367 @default.
• W3202192845 hasRelatedWork W2952791215 @default.
• W3202192845 hasRelatedWork W2966091943 @default.
• W3202192845 hasRelatedWork W3017479646 @default.
• W3202192845 hasRelatedWork W3023037531 @default.
• W3202192845 hasRelatedWork W3162218253 @default.
• W3202192845 hasRelatedWork W998841614 @default.
• W3202192845 hasRelatedWork W2471267854 @default.
• W3202192845 isParatext "false" @default.
• W3202192845 isRetracted "false" @default.
• W3202192845 magId "3202192845" @default.
• W3202192845 workType "dissertation" @default.