Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297752781> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4297752781 abstract "Deep neural networks (DNNs) have demonstrated state-of-the-art results on many pattern recognition tasks, especially vision classification problems. Understanding the inner workings of such computational brains is both fascinating basic science that is interesting in its own right - similar to why we study the human brain - and will enable researchers to further improve DNNs. One path to understanding how a neural network functions internally is to study what each of its neurons has learned to detect. One such method is called activation maximization (AM), which synthesizes an input (e.g. an image) that highly activates a neuron. Here we dramatically improve the qualitative state of the art of activation maximization by harnessing a powerful, learned prior: a deep generator network (DGN). The algorithm (1) generates qualitatively state-of-the-art synthetic images that look almost real, (2) reveals the features learned by each neuron in an interpretable way, (3) generalizes well to new datasets and somewhat well to different network architectures without requiring the prior to be relearned, and (4) can be considered as a high-quality generative method (in this case, by generating novel, creative, interesting, recognizable images)." @default.
- W4297752781 created "2022-10-01" @default.
- W4297752781 creator A5006797018 @default.
- W4297752781 creator A5045605838 @default.
- W4297752781 creator A5049659753 @default.
- W4297752781 creator A5070290355 @default.
- W4297752781 creator A5090113830 @default.
- W4297752781 date "2016-05-30" @default.
- W4297752781 modified "2023-09-30" @default.
- W4297752781 title "Synthesizing the preferred inputs for neurons in neural networks via deep generator networks" @default.
- W4297752781 doi "https://doi.org/10.48550/arxiv.1605.09304" @default.
- W4297752781 hasPublicationYear "2016" @default.
- W4297752781 type Work @default.
- W4297752781 citedByCount "5" @default.
- W4297752781 countsByYear W42977527812023 @default.
- W4297752781 crossrefType "posted-content" @default.
- W4297752781 hasAuthorship W4297752781A5006797018 @default.
- W4297752781 hasAuthorship W4297752781A5045605838 @default.
- W4297752781 hasAuthorship W4297752781A5049659753 @default.
- W4297752781 hasAuthorship W4297752781A5070290355 @default.
- W4297752781 hasAuthorship W4297752781A5090113830 @default.
- W4297752781 hasBestOaLocation W42977527811 @default.
- W4297752781 hasConcept C108583219 @default.
- W4297752781 hasConcept C11413529 @default.
- W4297752781 hasConcept C115961682 @default.
- W4297752781 hasConcept C119857082 @default.
- W4297752781 hasConcept C121332964 @default.
- W4297752781 hasConcept C126255220 @default.
- W4297752781 hasConcept C153180895 @default.
- W4297752781 hasConcept C154945302 @default.
- W4297752781 hasConcept C163258240 @default.
- W4297752781 hasConcept C199360897 @default.
- W4297752781 hasConcept C2776330181 @default.
- W4297752781 hasConcept C2777735758 @default.
- W4297752781 hasConcept C2780992000 @default.
- W4297752781 hasConcept C2984842247 @default.
- W4297752781 hasConcept C33923547 @default.
- W4297752781 hasConcept C39890363 @default.
- W4297752781 hasConcept C41008148 @default.
- W4297752781 hasConcept C48103436 @default.
- W4297752781 hasConcept C50644808 @default.
- W4297752781 hasConcept C62520636 @default.
- W4297752781 hasConceptScore W4297752781C108583219 @default.
- W4297752781 hasConceptScore W4297752781C11413529 @default.
- W4297752781 hasConceptScore W4297752781C115961682 @default.
- W4297752781 hasConceptScore W4297752781C119857082 @default.
- W4297752781 hasConceptScore W4297752781C121332964 @default.
- W4297752781 hasConceptScore W4297752781C126255220 @default.
- W4297752781 hasConceptScore W4297752781C153180895 @default.
- W4297752781 hasConceptScore W4297752781C154945302 @default.
- W4297752781 hasConceptScore W4297752781C163258240 @default.
- W4297752781 hasConceptScore W4297752781C199360897 @default.
- W4297752781 hasConceptScore W4297752781C2776330181 @default.
- W4297752781 hasConceptScore W4297752781C2777735758 @default.
- W4297752781 hasConceptScore W4297752781C2780992000 @default.
- W4297752781 hasConceptScore W4297752781C2984842247 @default.
- W4297752781 hasConceptScore W4297752781C33923547 @default.
- W4297752781 hasConceptScore W4297752781C39890363 @default.
- W4297752781 hasConceptScore W4297752781C41008148 @default.
- W4297752781 hasConceptScore W4297752781C48103436 @default.
- W4297752781 hasConceptScore W4297752781C50644808 @default.
- W4297752781 hasConceptScore W4297752781C62520636 @default.
- W4297752781 hasLocation W42977527811 @default.
- W4297752781 hasOpenAccess W4297752781 @default.
- W4297752781 hasPrimaryLocation W42977527811 @default.
- W4297752781 hasRelatedWork W2576264401 @default.
- W4297752781 hasRelatedWork W2773120646 @default.
- W4297752781 hasRelatedWork W2909645158 @default.
- W4297752781 hasRelatedWork W2950066684 @default.
- W4297752781 hasRelatedWork W3082895349 @default.
- W4297752781 hasRelatedWork W3162132941 @default.
- W4297752781 hasRelatedWork W3179488938 @default.
- W4297752781 hasRelatedWork W4288853838 @default.
- W4297752781 hasRelatedWork W4298388782 @default.
- W4297752781 hasRelatedWork W4312831135 @default.
- W4297752781 isParatext "false" @default.
- W4297752781 isRetracted "false" @default.
- W4297752781 workType "article" @default.