Matches in SemOpenAlex for { <https://semopenalex.org/work/W2957780671> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2957780671 abstract "Gaussian process [1] and it’s variants of deep structures like deep gaussian processes [2] and convolutional deep gaussian processes [3] are inherently equipped with a flexibility of encapsulating infinite order feature functions in their kernels and yet incorporating occam’s razor [4] to prevent overfitting. By stacking multitude of GPs, it becomes possible to manifest even a non-stationary version of the random process even with a stationary kernel at each and every layer. Using Doubly Stochastic Variational Inference [5], we study it’s performance on active learning based on certain acquisition functions. Convolutional Deep GP promises to be a good generalization for it’s counterpart, convolutional networks in non-bayesian Deep Neural Networks. Active learning [6] relies on learning from minimal amount of data and capitalizing the learned structure on acquiring data points whose identification is difficult to classify. The uncertainity estimates help in propagating the belief across network and make better confidence estimates which is not possible in non-bayesian topology. Also the non-probabilistic neural networks voraciously eat large chunk of data to make prediction that too without any uncertainity estimates. We also gauge caliberation of the learned deep GP model based on reliability diagram [7, 8] and certain uncertainity scores. We analyse the behaviour of the above model on unseen classes to figure out how much it can distinguish between what it has learned and what is completely new to it’s vision using similar uncertainity estimates as used for above analysis. We also conduct experiments on the same learned model to analyse it’s response to adversarial examples [9] to find how immune it is to such deceiving examples." @default.
- W2957780671 created "2019-07-23" @default.
- W2957780671 creator A5015678760 @default.
- W2957780671 creator A5040632547 @default.
- W2957780671 date "2019-01-01" @default.
- W2957780671 modified "2023-09-28" @default.
- W2957780671 title "Uncertainity quantification in Convolutional Deep Gaussian Process" @default.
- W2957780671 hasPublicationYear "2019" @default.
- W2957780671 type Work @default.
- W2957780671 sameAs 2957780671 @default.
- W2957780671 citedByCount "0" @default.
- W2957780671 crossrefType "dissertation" @default.
- W2957780671 hasAuthorship W2957780671A5015678760 @default.
- W2957780671 hasAuthorship W2957780671A5040632547 @default.
- W2957780671 hasConcept C108583219 @default.
- W2957780671 hasConcept C119857082 @default.
- W2957780671 hasConcept C121332964 @default.
- W2957780671 hasConcept C134306372 @default.
- W2957780671 hasConcept C154945302 @default.
- W2957780671 hasConcept C163716315 @default.
- W2957780671 hasConcept C177148314 @default.
- W2957780671 hasConcept C22019652 @default.
- W2957780671 hasConcept C33923547 @default.
- W2957780671 hasConcept C41008148 @default.
- W2957780671 hasConcept C50644808 @default.
- W2957780671 hasConcept C61326573 @default.
- W2957780671 hasConcept C62520636 @default.
- W2957780671 hasConcept C81363708 @default.
- W2957780671 hasConceptScore W2957780671C108583219 @default.
- W2957780671 hasConceptScore W2957780671C119857082 @default.
- W2957780671 hasConceptScore W2957780671C121332964 @default.
- W2957780671 hasConceptScore W2957780671C134306372 @default.
- W2957780671 hasConceptScore W2957780671C154945302 @default.
- W2957780671 hasConceptScore W2957780671C163716315 @default.
- W2957780671 hasConceptScore W2957780671C177148314 @default.
- W2957780671 hasConceptScore W2957780671C22019652 @default.
- W2957780671 hasConceptScore W2957780671C33923547 @default.
- W2957780671 hasConceptScore W2957780671C41008148 @default.
- W2957780671 hasConceptScore W2957780671C50644808 @default.
- W2957780671 hasConceptScore W2957780671C61326573 @default.
- W2957780671 hasConceptScore W2957780671C62520636 @default.
- W2957780671 hasConceptScore W2957780671C81363708 @default.
- W2957780671 hasLocation W29577806711 @default.
- W2957780671 hasOpenAccess W2957780671 @default.
- W2957780671 hasPrimaryLocation W29577806711 @default.
- W2957780671 hasRelatedWork W1831449718 @default.
- W2957780671 hasRelatedWork W2095897186 @default.
- W2957780671 hasRelatedWork W2148464528 @default.
- W2957780671 hasRelatedWork W2169797000 @default.
- W2957780671 hasRelatedWork W2346211548 @default.
- W2957780671 hasRelatedWork W2396730968 @default.
- W2957780671 hasRelatedWork W2767449908 @default.
- W2957780671 hasRelatedWork W2889705289 @default.
- W2957780671 hasRelatedWork W2948166700 @default.
- W2957780671 hasRelatedWork W2952721354 @default.
- W2957780671 hasRelatedWork W2962824341 @default.
- W2957780671 hasRelatedWork W2965519836 @default.
- W2957780671 hasRelatedWork W2979915069 @default.
- W2957780671 hasRelatedWork W2997153078 @default.
- W2957780671 hasRelatedWork W3003921671 @default.
- W2957780671 hasRelatedWork W3006861283 @default.
- W2957780671 hasRelatedWork W3120103717 @default.
- W2957780671 hasRelatedWork W3130823131 @default.
- W2957780671 hasRelatedWork W3209660231 @default.
- W2957780671 hasRelatedWork W586715238 @default.
- W2957780671 isParatext "false" @default.
- W2957780671 isRetracted "false" @default.
- W2957780671 magId "2957780671" @default.
- W2957780671 workType "dissertation" @default.