Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896600774> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2896600774 abstract "Anomaly detection is often considered a challenging field of machine learning due to the difficulty of obtaining anomalous samples for training and the need to obtain a sufficient amount of training data. In recent years, autoencoders have been shown to be effective anomaly detectors that train only on normal data. Generative adversarial networks (GANs) have been used to generate additional training samples for classifiers, thus making them more accurate and robust. However, in anomaly detection GANs are only used to reconstruct existing samples rather than to generate additional ones. This stems both from the small amount and lack of diversity of anomalous data in most domains. In this study we propose MDGAN, a novel GAN architecture for improving anomaly detection through the generation of additional samples. Our approach uses two discriminators: a dense network for determining whether the generated samples are of sufficient quality (i.e., valid) and an autoencoder that serves as an anomaly detector. MDGAN enables us to reconcile two conflicting goals: 1) generate high-quality samples that can fool the first discriminator, and 2) generate samples that can eventually be effectively reconstructed by the second discriminator, thus improving its performance. Empirical evaluation on a diverse set of datasets demonstrates the merits of our approach." @default.
- W2896600774 created "2018-10-26" @default.
- W2896600774 creator A5002391103 @default.
- W2896600774 creator A5017336017 @default.
- W2896600774 creator A5044390999 @default.
- W2896600774 date "2018-10-11" @default.
- W2896600774 modified "2023-10-14" @default.
- W2896600774 title "MDGAN: Boosting Anomaly Detection Using Multi-Discriminator Generative Adversarial Networks." @default.
- W2896600774 cites W1991357106 @default.
- W2896600774 cites W2122646361 @default.
- W2896600774 cites W2953267151 @default.
- W2896600774 hasPublicationYear "2018" @default.
- W2896600774 type Work @default.
- W2896600774 sameAs 2896600774 @default.
- W2896600774 citedByCount "4" @default.
- W2896600774 countsByYear W28966007742019 @default.
- W2896600774 countsByYear W28966007742021 @default.
- W2896600774 crossrefType "posted-content" @default.
- W2896600774 hasAuthorship W2896600774A5002391103 @default.
- W2896600774 hasAuthorship W2896600774A5017336017 @default.
- W2896600774 hasAuthorship W2896600774A5044390999 @default.
- W2896600774 hasConcept C101738243 @default.
- W2896600774 hasConcept C119857082 @default.
- W2896600774 hasConcept C121332964 @default.
- W2896600774 hasConcept C124101348 @default.
- W2896600774 hasConcept C12997251 @default.
- W2896600774 hasConcept C153180895 @default.
- W2896600774 hasConcept C154945302 @default.
- W2896600774 hasConcept C177264268 @default.
- W2896600774 hasConcept C199360897 @default.
- W2896600774 hasConcept C26873012 @default.
- W2896600774 hasConcept C2779803651 @default.
- W2896600774 hasConcept C39890363 @default.
- W2896600774 hasConcept C41008148 @default.
- W2896600774 hasConcept C46686674 @default.
- W2896600774 hasConcept C50644808 @default.
- W2896600774 hasConcept C51632099 @default.
- W2896600774 hasConcept C739882 @default.
- W2896600774 hasConcept C76155785 @default.
- W2896600774 hasConcept C94915269 @default.
- W2896600774 hasConceptScore W2896600774C101738243 @default.
- W2896600774 hasConceptScore W2896600774C119857082 @default.
- W2896600774 hasConceptScore W2896600774C121332964 @default.
- W2896600774 hasConceptScore W2896600774C124101348 @default.
- W2896600774 hasConceptScore W2896600774C12997251 @default.
- W2896600774 hasConceptScore W2896600774C153180895 @default.
- W2896600774 hasConceptScore W2896600774C154945302 @default.
- W2896600774 hasConceptScore W2896600774C177264268 @default.
- W2896600774 hasConceptScore W2896600774C199360897 @default.
- W2896600774 hasConceptScore W2896600774C26873012 @default.
- W2896600774 hasConceptScore W2896600774C2779803651 @default.
- W2896600774 hasConceptScore W2896600774C39890363 @default.
- W2896600774 hasConceptScore W2896600774C41008148 @default.
- W2896600774 hasConceptScore W2896600774C46686674 @default.
- W2896600774 hasConceptScore W2896600774C50644808 @default.
- W2896600774 hasConceptScore W2896600774C51632099 @default.
- W2896600774 hasConceptScore W2896600774C739882 @default.
- W2896600774 hasConceptScore W2896600774C76155785 @default.
- W2896600774 hasConceptScore W2896600774C94915269 @default.
- W2896600774 hasLocation W28966007741 @default.
- W2896600774 hasOpenAccess W2896600774 @default.
- W2896600774 hasPrimaryLocation W28966007741 @default.
- W2896600774 hasRelatedWork W2099471712 @default.
- W2896600774 hasRelatedWork W2599354622 @default.
- W2896600774 hasRelatedWork W2732428493 @default.
- W2896600774 hasRelatedWork W2901773810 @default.
- W2896600774 hasRelatedWork W2966734812 @default.
- W2896600774 hasRelatedWork W3023893564 @default.
- W2896600774 hasRelatedWork W3030609691 @default.
- W2896600774 hasRelatedWork W3034720584 @default.
- W2896600774 hasRelatedWork W3063636603 @default.
- W2896600774 hasRelatedWork W3089397955 @default.
- W2896600774 hasRelatedWork W309312769 @default.
- W2896600774 hasRelatedWork W3109541357 @default.
- W2896600774 hasRelatedWork W3114329625 @default.
- W2896600774 hasRelatedWork W3136173905 @default.
- W2896600774 hasRelatedWork W3138401877 @default.
- W2896600774 hasRelatedWork W3139079932 @default.
- W2896600774 hasRelatedWork W3157487903 @default.
- W2896600774 hasRelatedWork W3167305632 @default.
- W2896600774 hasRelatedWork W3193528524 @default.
- W2896600774 hasRelatedWork W3195426195 @default.
- W2896600774 isParatext "false" @default.
- W2896600774 isRetracted "false" @default.
- W2896600774 magId "2896600774" @default.
- W2896600774 workType "article" @default.