Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298042269> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4298042269 abstract "Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the brain optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, the neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network can learn to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful representations---the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the dendritic morphology of neocortical pyramidal neurons." @default.
- W4298042269 created "2022-10-01" @default.
- W4298042269 creator A5007668479 @default.
- W4298042269 creator A5021366411 @default.
- W4298042269 creator A5066294254 @default.
- W4298042269 date "2016-10-01" @default.
- W4298042269 modified "2023-09-27" @default.
- W4298042269 title "Towards deep learning with segregated dendrites" @default.
- W4298042269 doi "https://doi.org/10.48550/arxiv.1610.00161" @default.
- W4298042269 hasPublicationYear "2016" @default.
- W4298042269 type Work @default.
- W4298042269 citedByCount "0" @default.
- W4298042269 crossrefType "posted-content" @default.
- W4298042269 hasAuthorship W4298042269A5007668479 @default.
- W4298042269 hasAuthorship W4298042269A5021366411 @default.
- W4298042269 hasAuthorship W4298042269A5066294254 @default.
- W4298042269 hasBestOaLocation W42980422691 @default.
- W4298042269 hasConcept C108583219 @default.
- W4298042269 hasConcept C152478114 @default.
- W4298042269 hasConcept C154945302 @default.
- W4298042269 hasConcept C169760540 @default.
- W4298042269 hasConcept C41008148 @default.
- W4298042269 hasConcept C50644808 @default.
- W4298042269 hasConcept C66949984 @default.
- W4298042269 hasConcept C86803240 @default.
- W4298042269 hasConcept C94124525 @default.
- W4298042269 hasConcept C94487597 @default.
- W4298042269 hasConceptScore W4298042269C108583219 @default.
- W4298042269 hasConceptScore W4298042269C152478114 @default.
- W4298042269 hasConceptScore W4298042269C154945302 @default.
- W4298042269 hasConceptScore W4298042269C169760540 @default.
- W4298042269 hasConceptScore W4298042269C41008148 @default.
- W4298042269 hasConceptScore W4298042269C50644808 @default.
- W4298042269 hasConceptScore W4298042269C66949984 @default.
- W4298042269 hasConceptScore W4298042269C86803240 @default.
- W4298042269 hasConceptScore W4298042269C94124525 @default.
- W4298042269 hasConceptScore W4298042269C94487597 @default.
- W4298042269 hasLocation W42980422691 @default.
- W4298042269 hasOpenAccess W4298042269 @default.
- W4298042269 hasPrimaryLocation W42980422691 @default.
- W4298042269 hasRelatedWork W180750057 @default.
- W4298042269 hasRelatedWork W1976508877 @default.
- W4298042269 hasRelatedWork W2002497875 @default.
- W4298042269 hasRelatedWork W2012265686 @default.
- W4298042269 hasRelatedWork W2014230353 @default.
- W4298042269 hasRelatedWork W2112920381 @default.
- W4298042269 hasRelatedWork W2113133756 @default.
- W4298042269 hasRelatedWork W2158976454 @default.
- W4298042269 hasRelatedWork W2808304326 @default.
- W4298042269 hasRelatedWork W4292092500 @default.
- W4298042269 isParatext "false" @default.
- W4298042269 isRetracted "false" @default.
- W4298042269 workType "article" @default.