Matches in SemOpenAlex for { <https://semopenalex.org/work/W2275365310> ?p ?o ?g. }
- W2275365310 endingPage "1186" @default.
- W2275365310 startingPage "1177" @default.
- W2275365310 abstract "Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at inferring high-level invariant representations from unlabeled data. This paper presents a deep generative model with a possibly large external memory and an attention mechanism to capture the local detail information that is often lost in the bottom-up abstraction process in representation learning. By adopting a smooth attention model, the whole network is trained end-to-end by optimizing a variational bound of data likelihood via auto-encoding variational Bayesian methods, where an asymmetric recognition network is learnt jointly to infer high-level invariant representations. The asymmetric architecture can reduce the competition between bottom-up invariant feature extraction and top-down generation of instance details. Our experiments on several datasets demonstrate that memory can significantly boost the performance of DGMs on various tasks, including density estimation, image generation, and missing value imputation, and DGMs with memory can achieve state-of-the-art quantitative results." @default.
- W2275365310 created "2016-06-24" @default.
- W2275365310 creator A5003713785 @default.
- W2275365310 creator A5011877804 @default.
- W2275365310 creator A5072905534 @default.
- W2275365310 date "2016-06-19" @default.
- W2275365310 modified "2023-09-27" @default.
- W2275365310 title "Learning to generate with memory" @default.
- W2275365310 cites W1514535095 @default.
- W2275365310 cites W1531388653 @default.
- W2275365310 cites W1533861849 @default.
- W2275365310 cites W1602017060 @default.
- W2275365310 cites W1606347560 @default.
- W2275365310 cites W1665214252 @default.
- W2275365310 cites W1666690886 @default.
- W2275365310 cites W1810943226 @default.
- W2275365310 cites W1836465849 @default.
- W2275365310 cites W189596042 @default.
- W2275365310 cites W1959608418 @default.
- W2275365310 cites W2083380015 @default.
- W2275365310 cites W2097268041 @default.
- W2275365310 cites W2099471712 @default.
- W2275365310 cites W2103504761 @default.
- W2275365310 cites W2108501770 @default.
- W2275365310 cites W2112796928 @default.
- W2275365310 cites W2115595010 @default.
- W2275365310 cites W2125308790 @default.
- W2275365310 cites W2126398289 @default.
- W2275365310 cites W2135181320 @default.
- W2275365310 cites W2136922672 @default.
- W2275365310 cites W2141399712 @default.
- W2275365310 cites W2145094598 @default.
- W2275365310 cites W2147062276 @default.
- W2275365310 cites W2147527908 @default.
- W2275365310 cites W2157002241 @default.
- W2275365310 cites W2161133254 @default.
- W2275365310 cites W2163922914 @default.
- W2275365310 cites W2949416428 @default.
- W2275365310 cites W2950527759 @default.
- W2275365310 cites W2951008357 @default.
- W2275365310 cites W2951523806 @default.
- W2275365310 cites W2952278564 @default.
- W2275365310 cites W2953267151 @default.
- W2275365310 cites W2962741254 @default.
- W2275365310 cites W2962897886 @default.
- W2275365310 cites W2963275229 @default.
- W2275365310 cites W2963828071 @default.
- W2275365310 cites W2963857374 @default.
- W2275365310 cites W2964036520 @default.
- W2275365310 cites W2964121744 @default.
- W2275365310 cites W2964308564 @default.
- W2275365310 cites W3120740533 @default.
- W2275365310 cites W830076066 @default.
- W2275365310 cites W2584341106 @default.
- W2275365310 hasPublicationYear "2016" @default.
- W2275365310 type Work @default.
- W2275365310 sameAs 2275365310 @default.
- W2275365310 citedByCount "10" @default.
- W2275365310 countsByYear W22753653102017 @default.
- W2275365310 countsByYear W22753653102019 @default.
- W2275365310 countsByYear W22753653102020 @default.
- W2275365310 countsByYear W22753653102021 @default.
- W2275365310 countsByYear W22753653102022 @default.
- W2275365310 crossrefType "proceedings-article" @default.
- W2275365310 hasAuthorship W2275365310A5003713785 @default.
- W2275365310 hasAuthorship W2275365310A5011877804 @default.
- W2275365310 hasAuthorship W2275365310A5072905534 @default.
- W2275365310 hasConcept C108583219 @default.
- W2275365310 hasConcept C111472728 @default.
- W2275365310 hasConcept C119857082 @default.
- W2275365310 hasConcept C121332964 @default.
- W2275365310 hasConcept C124304363 @default.
- W2275365310 hasConcept C138885662 @default.
- W2275365310 hasConcept C153180895 @default.
- W2275365310 hasConcept C154945302 @default.
- W2275365310 hasConcept C167966045 @default.
- W2275365310 hasConcept C190470478 @default.
- W2275365310 hasConcept C37914503 @default.
- W2275365310 hasConcept C39890363 @default.
- W2275365310 hasConcept C41008148 @default.
- W2275365310 hasConceptScore W2275365310C108583219 @default.
- W2275365310 hasConceptScore W2275365310C111472728 @default.
- W2275365310 hasConceptScore W2275365310C119857082 @default.
- W2275365310 hasConceptScore W2275365310C121332964 @default.
- W2275365310 hasConceptScore W2275365310C124304363 @default.
- W2275365310 hasConceptScore W2275365310C138885662 @default.
- W2275365310 hasConceptScore W2275365310C153180895 @default.
- W2275365310 hasConceptScore W2275365310C154945302 @default.
- W2275365310 hasConceptScore W2275365310C167966045 @default.
- W2275365310 hasConceptScore W2275365310C190470478 @default.
- W2275365310 hasConceptScore W2275365310C37914503 @default.
- W2275365310 hasConceptScore W2275365310C39890363 @default.
- W2275365310 hasConceptScore W2275365310C41008148 @default.
- W2275365310 hasLocation W22753653101 @default.
- W2275365310 hasOpenAccess W2275365310 @default.
- W2275365310 hasPrimaryLocation W22753653101 @default.
- W2275365310 hasRelatedWork W1959608418 @default.
- W2275365310 hasRelatedWork W2112796928 @default.