Matches in SemOpenAlex for { <https://semopenalex.org/work/W2946809898> ?p ?o ?g. }
- W2946809898 abstract "The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly affected when a technique like batchnorm is used. As a result, hyperparameter optimization of deep networks can be much more challenging than traditional machine learning models. In this work, we start from well known Bayesian Optimization solutions and provide enhancement strategies specifically designed for hyperparameter optimization of deep networks. The resulting algorithm is named as DEEP-BO (Diversified, Early-termination-Enabled, and Parallel Bayesian Optimization). When evaluated over six DNN benchmarks, DEEP-BO easily outperforms or shows comparable performance with some of the well-known solutions including GP-Hedge, Hyperband, BOHB, Median Stopping Rule, and Learning Curve Extrapolation. The code used is made publicly available at this https URL." @default.
- W2946809898 created "2019-05-29" @default.
- W2946809898 creator A5023054084 @default.
- W2946809898 creator A5030649976 @default.
- W2946809898 creator A5050507605 @default.
- W2946809898 creator A5056032525 @default.
- W2946809898 creator A5058690796 @default.
- W2946809898 creator A5066676734 @default.
- W2946809898 date "2019-05-23" @default.
- W2946809898 modified "2023-09-27" @default.
- W2946809898 title "DEEP-BO for Hyperparameter Optimization of Deep Networks" @default.
- W2946809898 cites W1510052597 @default.
- W2946809898 cites W2016043834 @default.
- W2946809898 cites W2061144551 @default.
- W2946809898 cites W2093625674 @default.
- W2946809898 cites W2097998348 @default.
- W2946809898 cites W2106411961 @default.
- W2946809898 cites W2129766733 @default.
- W2946809898 cites W2131241448 @default.
- W2946809898 cites W2151554678 @default.
- W2946809898 cites W2175583736 @default.
- W2946809898 cites W2266822037 @default.
- W2946809898 cites W2296059279 @default.
- W2946809898 cites W2409689189 @default.
- W2946809898 cites W2553055651 @default.
- W2946809898 cites W2556372419 @default.
- W2946809898 cites W2583906999 @default.
- W2946809898 cites W2614311475 @default.
- W2946809898 cites W2616619952 @default.
- W2946809898 cites W2732547613 @default.
- W2946809898 cites W2751836095 @default.
- W2946809898 cites W2783201493 @default.
- W2946809898 cites W2805902845 @default.
- W2946809898 cites W2919302225 @default.
- W2946809898 cites W2963110737 @default.
- W2946809898 cites W2963423218 @default.
- W2946809898 cites W2964136676 @default.
- W2946809898 cites W2964294659 @default.
- W2946809898 cites W3102150134 @default.
- W2946809898 cites W3124229194 @default.
- W2946809898 cites W60686164 @default.
- W2946809898 hasPublicationYear "2019" @default.
- W2946809898 type Work @default.
- W2946809898 sameAs 2946809898 @default.
- W2946809898 citedByCount "0" @default.
- W2946809898 crossrefType "posted-content" @default.
- W2946809898 hasAuthorship W2946809898A5023054084 @default.
- W2946809898 hasAuthorship W2946809898A5030649976 @default.
- W2946809898 hasAuthorship W2946809898A5050507605 @default.
- W2946809898 hasAuthorship W2946809898A5056032525 @default.
- W2946809898 hasAuthorship W2946809898A5058690796 @default.
- W2946809898 hasAuthorship W2946809898A5066676734 @default.
- W2946809898 hasConcept C10485038 @default.
- W2946809898 hasConcept C105795698 @default.
- W2946809898 hasConcept C108583219 @default.
- W2946809898 hasConcept C11413529 @default.
- W2946809898 hasConcept C119857082 @default.
- W2946809898 hasConcept C12267149 @default.
- W2946809898 hasConcept C126255220 @default.
- W2946809898 hasConcept C132459708 @default.
- W2946809898 hasConcept C154945302 @default.
- W2946809898 hasConcept C177264268 @default.
- W2946809898 hasConcept C199360897 @default.
- W2946809898 hasConcept C2776760102 @default.
- W2946809898 hasConcept C2778049539 @default.
- W2946809898 hasConcept C2983961125 @default.
- W2946809898 hasConcept C2984842247 @default.
- W2946809898 hasConcept C33923547 @default.
- W2946809898 hasConcept C41008148 @default.
- W2946809898 hasConcept C50644808 @default.
- W2946809898 hasConcept C8642999 @default.
- W2946809898 hasConceptScore W2946809898C10485038 @default.
- W2946809898 hasConceptScore W2946809898C105795698 @default.
- W2946809898 hasConceptScore W2946809898C108583219 @default.
- W2946809898 hasConceptScore W2946809898C11413529 @default.
- W2946809898 hasConceptScore W2946809898C119857082 @default.
- W2946809898 hasConceptScore W2946809898C12267149 @default.
- W2946809898 hasConceptScore W2946809898C126255220 @default.
- W2946809898 hasConceptScore W2946809898C132459708 @default.
- W2946809898 hasConceptScore W2946809898C154945302 @default.
- W2946809898 hasConceptScore W2946809898C177264268 @default.
- W2946809898 hasConceptScore W2946809898C199360897 @default.
- W2946809898 hasConceptScore W2946809898C2776760102 @default.
- W2946809898 hasConceptScore W2946809898C2778049539 @default.
- W2946809898 hasConceptScore W2946809898C2983961125 @default.
- W2946809898 hasConceptScore W2946809898C2984842247 @default.
- W2946809898 hasConceptScore W2946809898C33923547 @default.
- W2946809898 hasConceptScore W2946809898C41008148 @default.
- W2946809898 hasConceptScore W2946809898C50644808 @default.
- W2946809898 hasConceptScore W2946809898C8642999 @default.
- W2946809898 hasLocation W29468098981 @default.
- W2946809898 hasOpenAccess W2946809898 @default.
- W2946809898 hasPrimaryLocation W29468098981 @default.
- W2946809898 hasRelatedWork W2743024835 @default.
- W2946809898 hasRelatedWork W2753657222 @default.
- W2946809898 hasRelatedWork W2791139006 @default.
- W2946809898 hasRelatedWork W2895674636 @default.
- W2946809898 hasRelatedWork W2963452728 @default.
- W2946809898 hasRelatedWork W2966247750 @default.
- W2946809898 hasRelatedWork W2980377888 @default.