Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287639457> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4287639457 abstract "Although a number of studies have explored deep learning in neuroscience, the application of these algorithms to neural systems on a microscopic scale, i.e. parameters relevant to lower scales of organization, remains relatively novel. Motivated by advances in whole-brain imaging, we examined the performance of deep learning models on microscopic neural dynamics and resulting emergent behaviors using calcium imaging data from the nematode C. elegans. We show that neural networks perform remarkably well on both neuron-level dynamics prediction, and behavioral state classification. In addition, we compared the performance of structure agnostic neural networks and graph neural networks to investigate if graph structure can be exploited as a favorable inductive bias. To perform this experiment, we designed a graph neural network which explicitly infers relations between neurons from neural activity and leverages the inferred graph structure during computations. In our experiments, we found that graph neural networks generally outperformed structure agnostic models and excel in generalization on unseen organisms, implying a potential path to generalizable machine learning in neuroscience." @default.
- W4287639457 created "2022-07-25" @default.
- W4287639457 creator A5004370458 @default.
- W4287639457 creator A5027519087 @default.
- W4287639457 creator A5048013953 @default.
- W4287639457 creator A5073467232 @default.
- W4287639457 date "2020-10-16" @default.
- W4287639457 modified "2023-10-17" @default.
- W4287639457 title "Generalizable Machine Learning in Neuroscience using Graph Neural Networks" @default.
- W4287639457 doi "https://doi.org/10.48550/arxiv.2010.08569" @default.
- W4287639457 hasPublicationYear "2020" @default.
- W4287639457 type Work @default.
- W4287639457 citedByCount "0" @default.
- W4287639457 crossrefType "posted-content" @default.
- W4287639457 hasAuthorship W4287639457A5004370458 @default.
- W4287639457 hasAuthorship W4287639457A5027519087 @default.
- W4287639457 hasAuthorship W4287639457A5048013953 @default.
- W4287639457 hasAuthorship W4287639457A5073467232 @default.
- W4287639457 hasBestOaLocation W42876394571 @default.
- W4287639457 hasConcept C108583219 @default.
- W4287639457 hasConcept C118403218 @default.
- W4287639457 hasConcept C119857082 @default.
- W4287639457 hasConcept C132525143 @default.
- W4287639457 hasConcept C15286952 @default.
- W4287639457 hasConcept C154945302 @default.
- W4287639457 hasConcept C15744967 @default.
- W4287639457 hasConcept C169760540 @default.
- W4287639457 hasConcept C2776985911 @default.
- W4287639457 hasConcept C2778609137 @default.
- W4287639457 hasConcept C31288803 @default.
- W4287639457 hasConcept C41008148 @default.
- W4287639457 hasConcept C50644808 @default.
- W4287639457 hasConcept C529278444 @default.
- W4287639457 hasConcept C80444323 @default.
- W4287639457 hasConceptScore W4287639457C108583219 @default.
- W4287639457 hasConceptScore W4287639457C118403218 @default.
- W4287639457 hasConceptScore W4287639457C119857082 @default.
- W4287639457 hasConceptScore W4287639457C132525143 @default.
- W4287639457 hasConceptScore W4287639457C15286952 @default.
- W4287639457 hasConceptScore W4287639457C154945302 @default.
- W4287639457 hasConceptScore W4287639457C15744967 @default.
- W4287639457 hasConceptScore W4287639457C169760540 @default.
- W4287639457 hasConceptScore W4287639457C2776985911 @default.
- W4287639457 hasConceptScore W4287639457C2778609137 @default.
- W4287639457 hasConceptScore W4287639457C31288803 @default.
- W4287639457 hasConceptScore W4287639457C41008148 @default.
- W4287639457 hasConceptScore W4287639457C50644808 @default.
- W4287639457 hasConceptScore W4287639457C529278444 @default.
- W4287639457 hasConceptScore W4287639457C80444323 @default.
- W4287639457 hasLocation W42876394571 @default.
- W4287639457 hasOpenAccess W4287639457 @default.
- W4287639457 hasPrimaryLocation W42876394571 @default.
- W4287639457 hasRelatedWork W10924315 @default.
- W4287639457 hasRelatedWork W11375610 @default.
- W4287639457 hasRelatedWork W13678974 @default.
- W4287639457 hasRelatedWork W13747797 @default.
- W4287639457 hasRelatedWork W7524991 @default.
- W4287639457 hasRelatedWork W8021486 @default.
- W4287639457 hasRelatedWork W8249623 @default.
- W4287639457 hasRelatedWork W8994160 @default.
- W4287639457 hasRelatedWork W9190101 @default.
- W4287639457 hasRelatedWork W9333608 @default.
- W4287639457 isParatext "false" @default.
- W4287639457 isRetracted "false" @default.
- W4287639457 workType "article" @default.