Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200745262> ?p ?o ?g. }
- W3200745262 abstract "This paper presents a probabilistic framework to obtain both reliable and fast uncertainty estimates for predictions with Deep Neural Networks (DNNs). Our main contribution is a practical and principled combination of DNNs with sparse Gaussian Processes (GPs). We prove theoretically that DNNs can be seen as a special case of sparse GPs, namely mixtures of GP experts (MoE-GP), and we devise a learning algorithm that brings the derived theory into practice. In experiments from two different robotic tasks -- inverse dynamics of a manipulator and object detection on a micro-aerial vehicle (MAV) -- we show the effectiveness of our approach in terms of predictive uncertainty, improved scalability, and run-time efficiency on a Jetson TX2. We thus argue that our approach can pave the way towards reliable and fast robot learning systems with uncertainty awareness." @default.
- W3200745262 created "2021-09-27" @default.
- W3200745262 creator A5014313436 @default.
- W3200745262 creator A5033653599 @default.
- W3200745262 creator A5047422102 @default.
- W3200745262 creator A5050478468 @default.
- W3200745262 creator A5070809739 @default.
- W3200745262 date "2021-09-20" @default.
- W3200745262 modified "2023-09-26" @default.
- W3200745262 title "Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes" @default.
- W3200745262 cites W1173687456 @default.
- W3200745262 cites W164706946 @default.
- W3200745262 cites W1663973292 @default.
- W3200745262 cites W1986007546 @default.
- W3200745262 cites W2003768689 @default.
- W3200745262 cites W2047244756 @default.
- W3200745262 cites W2099242680 @default.
- W3200745262 cites W2115305054 @default.
- W3200745262 cites W2122377431 @default.
- W3200745262 cites W2130031702 @default.
- W3200745262 cites W2137956165 @default.
- W3200745262 cites W2150884987 @default.
- W3200745262 cites W2336416123 @default.
- W3200745262 cites W2467155776 @default.
- W3200745262 cites W2542075568 @default.
- W3200745262 cites W2734960757 @default.
- W3200745262 cites W2761882052 @default.
- W3200745262 cites W2786857698 @default.
- W3200745262 cites W2806471870 @default.
- W3200745262 cites W2809090039 @default.
- W3200745262 cites W2909720712 @default.
- W3200745262 cites W2955023002 @default.
- W3200745262 cites W2962935959 @default.
- W3200745262 cites W2962996090 @default.
- W3200745262 cites W2963179241 @default.
- W3200745262 cites W2963238274 @default.
- W3200745262 cites W2963254338 @default.
- W3200745262 cites W2964052793 @default.
- W3200745262 cites W2964059111 @default.
- W3200745262 cites W2964135722 @default.
- W3200745262 cites W2964212410 @default.
- W3200745262 cites W2970111740 @default.
- W3200745262 cites W2972628643 @default.
- W3200745262 cites W2981482273 @default.
- W3200745262 cites W2995449755 @default.
- W3200745262 cites W2995969761 @default.
- W3200745262 cites W3000508506 @default.
- W3200745262 cites W3012528573 @default.
- W3200745262 cites W3031208025 @default.
- W3200745262 cites W3035124332 @default.
- W3200745262 cites W3035387695 @default.
- W3200745262 cites W3035542331 @default.
- W3200745262 cites W3036332271 @default.
- W3200745262 cites W3037275730 @default.
- W3200745262 cites W3040904863 @default.
- W3200745262 cites W3042158842 @default.
- W3200745262 cites W3043009712 @default.
- W3200745262 cites W3090204745 @default.
- W3200745262 cites W3091218135 @default.
- W3200745262 cites W3095936509 @default.
- W3200745262 cites W3096609285 @default.
- W3200745262 cites W3103185335 @default.
- W3200745262 cites W3121172155 @default.
- W3200745262 cites W3127216037 @default.
- W3200745262 cites W3134774296 @default.
- W3200745262 cites W3183048323 @default.
- W3200745262 cites W3186504155 @default.
- W3200745262 cites W3202763387 @default.
- W3200745262 hasPublicationYear "2021" @default.
- W3200745262 type Work @default.
- W3200745262 sameAs 3200745262 @default.
- W3200745262 citedByCount "0" @default.
- W3200745262 crossrefType "posted-content" @default.
- W3200745262 hasAuthorship W3200745262A5014313436 @default.
- W3200745262 hasAuthorship W3200745262A5033653599 @default.
- W3200745262 hasAuthorship W3200745262A5047422102 @default.
- W3200745262 hasAuthorship W3200745262A5050478468 @default.
- W3200745262 hasAuthorship W3200745262A5070809739 @default.
- W3200745262 hasConcept C119857082 @default.
- W3200745262 hasConcept C121332964 @default.
- W3200745262 hasConcept C154945302 @default.
- W3200745262 hasConcept C163716315 @default.
- W3200745262 hasConcept C187523126 @default.
- W3200745262 hasConcept C2984842247 @default.
- W3200745262 hasConcept C34413123 @default.
- W3200745262 hasConcept C39920418 @default.
- W3200745262 hasConcept C41008148 @default.
- W3200745262 hasConcept C48044578 @default.
- W3200745262 hasConcept C49937458 @default.
- W3200745262 hasConcept C50644808 @default.
- W3200745262 hasConcept C60229501 @default.
- W3200745262 hasConcept C61326573 @default.
- W3200745262 hasConcept C62520636 @default.
- W3200745262 hasConcept C74650414 @default.
- W3200745262 hasConcept C76155785 @default.
- W3200745262 hasConcept C77088390 @default.
- W3200745262 hasConcept C90509273 @default.
- W3200745262 hasConceptScore W3200745262C119857082 @default.
- W3200745262 hasConceptScore W3200745262C121332964 @default.
- W3200745262 hasConceptScore W3200745262C154945302 @default.