Matches in SemOpenAlex for { <https://semopenalex.org/work/W3006989712> ?p ?o ?g. }
- W3006989712 abstract "Continual Learning is a learning paradigm where learning systems are trained with sequential or streaming tasks. Two notable directions among the recent advances in continual learning with neural networks are ($i$) variational Bayes based regularization by learning priors from previous tasks, and, ($ii$) learning the structure of deep networks to adapt to new tasks. So far, these two approaches have been orthogonal. We present a novel Bayesian approach to continual learning based on learning the structure of deep neural networks, addressing the shortcomings of both these approaches. The proposed model learns the deep structure for each task by learning which weights to be used, and supports inter-task transfer through the overlapping of different sparse subsets of weights learned by different tasks. Experimental results on supervised and unsupervised benchmarks shows that our model performs comparably or better than recent advances in continual learning setting." @default.
- W3006989712 created "2020-03-06" @default.
- W3006989712 creator A5021117952 @default.
- W3006989712 creator A5029651089 @default.
- W3006989712 creator A5035605156 @default.
- W3006989712 date "2019-12-08" @default.
- W3006989712 modified "2023-09-26" @default.
- W3006989712 title "Bayesian Structure Adaptation for Continual Learning" @default.
- W3006989712 cites W1584431645 @default.
- W3006989712 cites W1959608418 @default.
- W3006989712 cites W1973264045 @default.
- W3006989712 cites W2104827998 @default.
- W3006989712 cites W2116522068 @default.
- W3006989712 cites W2126658427 @default.
- W3006989712 cites W2158760659 @default.
- W3006989712 cites W2165698076 @default.
- W3006989712 cites W218059538 @default.
- W3006989712 cites W2293292859 @default.
- W3006989712 cites W2547875792 @default.
- W3006989712 cites W2548228487 @default.
- W3006989712 cites W2560647685 @default.
- W3006989712 cites W2567691283 @default.
- W3006989712 cites W2583761661 @default.
- W3006989712 cites W2737492962 @default.
- W3006989712 cites W2782276075 @default.
- W3006989712 cites W2787803546 @default.
- W3006989712 cites W2788388592 @default.
- W3006989712 cites W2804175194 @default.
- W3006989712 cites W2804802260 @default.
- W3006989712 cites W2896084542 @default.
- W3006989712 cites W2898892019 @default.
- W3006989712 cites W2902417425 @default.
- W3006989712 cites W2906141031 @default.
- W3006989712 cites W2912515466 @default.
- W3006989712 cites W2922466325 @default.
- W3006989712 cites W2925426609 @default.
- W3006989712 cites W2932484476 @default.
- W3006989712 cites W2945769336 @default.
- W3006989712 cites W2949995560 @default.
- W3006989712 cites W2951266961 @default.
- W3006989712 cites W2962724315 @default.
- W3006989712 cites W2963533215 @default.
- W3006989712 cites W2963540014 @default.
- W3006989712 cites W2963577698 @default.
- W3006989712 cites W2963850662 @default.
- W3006989712 cites W2964088867 @default.
- W3006989712 cites W2964188939 @default.
- W3006989712 cites W2970502342 @default.
- W3006989712 cites W2991265870 @default.
- W3006989712 cites W2993910441 @default.
- W3006989712 hasPublicationYear "2019" @default.
- W3006989712 type Work @default.
- W3006989712 sameAs 3006989712 @default.
- W3006989712 citedByCount "3" @default.
- W3006989712 countsByYear W30069897122019 @default.
- W3006989712 countsByYear W30069897122020 @default.
- W3006989712 countsByYear W30069897122021 @default.
- W3006989712 crossrefType "posted-content" @default.
- W3006989712 hasAuthorship W3006989712A5021117952 @default.
- W3006989712 hasAuthorship W3006989712A5029651089 @default.
- W3006989712 hasAuthorship W3006989712A5035605156 @default.
- W3006989712 hasConcept C107673813 @default.
- W3006989712 hasConcept C108583219 @default.
- W3006989712 hasConcept C119857082 @default.
- W3006989712 hasConcept C150899416 @default.
- W3006989712 hasConcept C154945302 @default.
- W3006989712 hasConcept C162324750 @default.
- W3006989712 hasConcept C177769412 @default.
- W3006989712 hasConcept C187736073 @default.
- W3006989712 hasConcept C207201462 @default.
- W3006989712 hasConcept C24138899 @default.
- W3006989712 hasConcept C2776135515 @default.
- W3006989712 hasConcept C2780451532 @default.
- W3006989712 hasConcept C28006648 @default.
- W3006989712 hasConcept C2984842247 @default.
- W3006989712 hasConcept C41008148 @default.
- W3006989712 hasConcept C50644808 @default.
- W3006989712 hasConcept C58973888 @default.
- W3006989712 hasConcept C8038995 @default.
- W3006989712 hasConceptScore W3006989712C107673813 @default.
- W3006989712 hasConceptScore W3006989712C108583219 @default.
- W3006989712 hasConceptScore W3006989712C119857082 @default.
- W3006989712 hasConceptScore W3006989712C150899416 @default.
- W3006989712 hasConceptScore W3006989712C154945302 @default.
- W3006989712 hasConceptScore W3006989712C162324750 @default.
- W3006989712 hasConceptScore W3006989712C177769412 @default.
- W3006989712 hasConceptScore W3006989712C187736073 @default.
- W3006989712 hasConceptScore W3006989712C207201462 @default.
- W3006989712 hasConceptScore W3006989712C24138899 @default.
- W3006989712 hasConceptScore W3006989712C2776135515 @default.
- W3006989712 hasConceptScore W3006989712C2780451532 @default.
- W3006989712 hasConceptScore W3006989712C28006648 @default.
- W3006989712 hasConceptScore W3006989712C2984842247 @default.
- W3006989712 hasConceptScore W3006989712C41008148 @default.
- W3006989712 hasConceptScore W3006989712C50644808 @default.
- W3006989712 hasConceptScore W3006989712C58973888 @default.
- W3006989712 hasConceptScore W3006989712C8038995 @default.
- W3006989712 hasLocation W30069897121 @default.
- W3006989712 hasOpenAccess W3006989712 @default.
- W3006989712 hasPrimaryLocation W30069897121 @default.