Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035162526> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W3035162526 endingPage "9503" @default.
- W3035162526 startingPage "9493" @default.
- W3035162526 abstract "We introduce a class of auto-encoder neural networks tailored to data from the natural exponential family (e.g., count data). The architectures are inspired by the problem of learning the filters in a convolutional generative model with sparsity constraints, often referred to as convolutional dictionary learning (CDL). Our work is the first to combine ideas from convolutional generative models and deep learning for data that are naturally modeled with a non-Gaussian distribution (e.g., binomial and Poisson). This perspective provides us with a scalable and flexible framework that can be re-purposed for a wide range of tasks and assumptions on the generative model. Specifically, the iterative optimization procedure for solving CDL, an unsupervised task, is mapped to an unfolded and constrained neural network, with iterative adjustments to the inputs to account for the generative distribution. We also show that the framework can easily be extended for discriminative training, appropriate for a supervised task. We demonstrate 1) that fitting the generative model to learn, in an unsupervised fashion, the latent stimulus that underlies neural spiking data leads to better goodness-of-fit compared to other baselines, 2) competitive performance compared to state-of-the-art algorithms for supervised Poisson image denoising, with significantly fewer parameters, and 3) gradient dynamics of shallow binomial auto-encoder." @default.
- W3035162526 created "2020-06-19" @default.
- W3035162526 creator A5002643771 @default.
- W3035162526 creator A5059156505 @default.
- W3035162526 creator A5066569995 @default.
- W3035162526 creator A5088730122 @default.
- W3035162526 date "2020-07-12" @default.
- W3035162526 modified "2023-09-23" @default.
- W3035162526 title "Convolutional dictionary learning based auto-encoders for natural exponential-family distributions" @default.
- W3035162526 hasPublicationYear "2020" @default.
- W3035162526 type Work @default.
- W3035162526 sameAs 3035162526 @default.
- W3035162526 citedByCount "4" @default.
- W3035162526 countsByYear W30351625262020 @default.
- W3035162526 countsByYear W30351625262021 @default.
- W3035162526 crossrefType "proceedings-article" @default.
- W3035162526 hasAuthorship W3035162526A5002643771 @default.
- W3035162526 hasAuthorship W3035162526A5059156505 @default.
- W3035162526 hasAuthorship W3035162526A5066569995 @default.
- W3035162526 hasAuthorship W3035162526A5088730122 @default.
- W3035162526 hasConcept C119857082 @default.
- W3035162526 hasConcept C153180895 @default.
- W3035162526 hasConcept C154945302 @default.
- W3035162526 hasConcept C167966045 @default.
- W3035162526 hasConcept C39890363 @default.
- W3035162526 hasConcept C41008148 @default.
- W3035162526 hasConcept C8038995 @default.
- W3035162526 hasConcept C81363708 @default.
- W3035162526 hasConcept C97931131 @default.
- W3035162526 hasConceptScore W3035162526C119857082 @default.
- W3035162526 hasConceptScore W3035162526C153180895 @default.
- W3035162526 hasConceptScore W3035162526C154945302 @default.
- W3035162526 hasConceptScore W3035162526C167966045 @default.
- W3035162526 hasConceptScore W3035162526C39890363 @default.
- W3035162526 hasConceptScore W3035162526C41008148 @default.
- W3035162526 hasConceptScore W3035162526C8038995 @default.
- W3035162526 hasConceptScore W3035162526C81363708 @default.
- W3035162526 hasConceptScore W3035162526C97931131 @default.
- W3035162526 hasOpenAccess W3035162526 @default.
- W3035162526 hasRelatedWork W156476889 @default.
- W3035162526 hasRelatedWork W2099732049 @default.
- W3035162526 hasRelatedWork W2123257246 @default.
- W3035162526 hasRelatedWork W2186324084 @default.
- W3035162526 hasRelatedWork W2188365844 @default.
- W3035162526 hasRelatedWork W2554952599 @default.
- W3035162526 hasRelatedWork W2581879608 @default.
- W3035162526 hasRelatedWork W2784283104 @default.
- W3035162526 hasRelatedWork W2803164693 @default.
- W3035162526 hasRelatedWork W2890850650 @default.
- W3035162526 hasRelatedWork W2896335160 @default.
- W3035162526 hasRelatedWork W2940245516 @default.
- W3035162526 hasRelatedWork W2950920935 @default.
- W3035162526 hasRelatedWork W2964335397 @default.
- W3035162526 hasRelatedWork W2981411377 @default.
- W3035162526 hasRelatedWork W3040915569 @default.
- W3035162526 hasRelatedWork W3153273997 @default.
- W3035162526 hasRelatedWork W3161942977 @default.
- W3035162526 hasRelatedWork W3163692982 @default.
- W3035162526 hasRelatedWork W3178784547 @default.
- W3035162526 hasVolume "1" @default.
- W3035162526 isParatext "false" @default.
- W3035162526 isRetracted "false" @default.
- W3035162526 magId "3035162526" @default.
- W3035162526 workType "article" @default.