Matches in SemOpenAlex for { <https://semopenalex.org/work/W152093217> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W152093217 abstract "The reliable application of machine learning methods becomes increasingly important in challenging engineering domains. In particular, the application of extremelearning machines (ELM) seems promising because of their apparent simplicity and the capability of very efficient processing of large and high-dimensional data sets.However, the ELM paradigm is based on the concept of single hidden-layer neural networks with randomly initialized and fixed input weights and is thus inherentlyunreliable. This black-box character usually repels engineers from application in potentially safety critical tasks. The problem becomes even more severe since, inprinciple, only sparse and noisy data sets can be provided in such domains. The goal of this thesis is therefore to equip the ELM approach with the abilities to perform in a reliable manner.This goal is approached in three aspects by enhancing the robustness of ELMs to initializations, make ELMs able to handle slow changes in the environment (i.e. input drifts), and allow the incorporation of continuous constraints derived from prior knowledge. It is shown in several diverse scenarios that the novel ELM approach proposed in this thesis ensures a safe and reliable application while simultaneously sustaining the full modeling power of data-driven methods." @default.
- W152093217 created "2016-06-24" @default.
- W152093217 creator A5023545882 @default.
- W152093217 date "2014-01-01" @default.
- W152093217 modified "2023-09-27" @default.
- W152093217 title "Reliability of Extreme Learning Machines" @default.
- W152093217 hasPublicationYear "2014" @default.
- W152093217 type Work @default.
- W152093217 sameAs 152093217 @default.
- W152093217 citedByCount "1" @default.
- W152093217 countsByYear W1520932172014 @default.
- W152093217 crossrefType "journal-article" @default.
- W152093217 hasAuthorship W152093217A5023545882 @default.
- W152093217 hasConcept C104317684 @default.
- W152093217 hasConcept C119857082 @default.
- W152093217 hasConcept C121332964 @default.
- W152093217 hasConcept C154945302 @default.
- W152093217 hasConcept C163258240 @default.
- W152093217 hasConcept C185592680 @default.
- W152093217 hasConcept C2780150128 @default.
- W152093217 hasConcept C41008148 @default.
- W152093217 hasConcept C43214815 @default.
- W152093217 hasConcept C50644808 @default.
- W152093217 hasConcept C55493867 @default.
- W152093217 hasConcept C62520636 @default.
- W152093217 hasConcept C63479239 @default.
- W152093217 hasConceptScore W152093217C104317684 @default.
- W152093217 hasConceptScore W152093217C119857082 @default.
- W152093217 hasConceptScore W152093217C121332964 @default.
- W152093217 hasConceptScore W152093217C154945302 @default.
- W152093217 hasConceptScore W152093217C163258240 @default.
- W152093217 hasConceptScore W152093217C185592680 @default.
- W152093217 hasConceptScore W152093217C2780150128 @default.
- W152093217 hasConceptScore W152093217C41008148 @default.
- W152093217 hasConceptScore W152093217C43214815 @default.
- W152093217 hasConceptScore W152093217C50644808 @default.
- W152093217 hasConceptScore W152093217C55493867 @default.
- W152093217 hasConceptScore W152093217C62520636 @default.
- W152093217 hasConceptScore W152093217C63479239 @default.
- W152093217 hasLocation W1520932171 @default.
- W152093217 hasOpenAccess W152093217 @default.
- W152093217 hasPrimaryLocation W1520932171 @default.
- W152093217 hasRelatedWork W189896577 @default.
- W152093217 hasRelatedWork W2185562387 @default.
- W152093217 hasRelatedWork W2263490141 @default.
- W152093217 hasRelatedWork W2598674267 @default.
- W152093217 hasRelatedWork W2769713526 @default.
- W152093217 hasRelatedWork W2904036825 @default.
- W152093217 hasRelatedWork W2914973938 @default.
- W152093217 hasRelatedWork W2916414436 @default.
- W152093217 hasRelatedWork W292279636 @default.
- W152093217 hasRelatedWork W2945374320 @default.
- W152093217 hasRelatedWork W2952631604 @default.
- W152093217 hasRelatedWork W2962924847 @default.
- W152093217 hasRelatedWork W2963509048 @default.
- W152093217 hasRelatedWork W2978369365 @default.
- W152093217 hasRelatedWork W3008314020 @default.
- W152093217 hasRelatedWork W3041850385 @default.
- W152093217 hasRelatedWork W3089200980 @default.
- W152093217 hasRelatedWork W3133013352 @default.
- W152093217 hasRelatedWork W3168712515 @default.
- W152093217 hasRelatedWork W3177179707 @default.
- W152093217 isParatext "false" @default.
- W152093217 isRetracted "false" @default.
- W152093217 magId "152093217" @default.
- W152093217 workType "article" @default.