Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951061345> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W2951061345 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.
- W2951061345 created "2019-06-27" @default.
- W2951061345 creator A5007668479 @default.
- W2951061345 creator A5021366411 @default.
- W2951061345 creator A5066294254 @default.
- W2951061345 date "2016-10-01" @default.
- W2951061345 modified "2023-09-27" @default.
- W2951061345 title "Towards deep learning with segregated dendrites" @default.
- W2951061345 hasPublicationYear "2016" @default.
- W2951061345 type Work @default.
- W2951061345 sameAs 2951061345 @default.
- W2951061345 citedByCount "4" @default.
- W2951061345 countsByYear W29510613452018 @default.
- W2951061345 countsByYear W29510613452019 @default.
- W2951061345 countsByYear W29510613452020 @default.
- W2951061345 crossrefType "posted-content" @default.
- W2951061345 hasAuthorship W2951061345A5007668479 @default.
- W2951061345 hasAuthorship W2951061345A5021366411 @default.
- W2951061345 hasAuthorship W2951061345A5066294254 @default.
- W2951061345 hasConcept C108583219 @default.
- W2951061345 hasConcept C152478114 @default.
- W2951061345 hasConcept C154945302 @default.
- W2951061345 hasConcept C169760540 @default.
- W2951061345 hasConcept C41008148 @default.
- W2951061345 hasConcept C50644808 @default.
- W2951061345 hasConcept C66949984 @default.
- W2951061345 hasConcept C86803240 @default.
- W2951061345 hasConcept C94124525 @default.
- W2951061345 hasConcept C94487597 @default.
- W2951061345 hasConceptScore W2951061345C108583219 @default.
- W2951061345 hasConceptScore W2951061345C152478114 @default.
- W2951061345 hasConceptScore W2951061345C154945302 @default.
- W2951061345 hasConceptScore W2951061345C169760540 @default.
- W2951061345 hasConceptScore W2951061345C41008148 @default.
- W2951061345 hasConceptScore W2951061345C50644808 @default.
- W2951061345 hasConceptScore W2951061345C66949984 @default.
- W2951061345 hasConceptScore W2951061345C86803240 @default.
- W2951061345 hasConceptScore W2951061345C94124525 @default.
- W2951061345 hasConceptScore W2951061345C94487597 @default.
- W2951061345 hasLocation W29510613451 @default.
- W2951061345 hasOpenAccess W2951061345 @default.
- W2951061345 hasPrimaryLocation W29510613451 @default.
- W2951061345 hasRelatedWork W1579411065 @default.
- W2951061345 hasRelatedWork W159324800 @default.
- W2951061345 hasRelatedWork W2190490644 @default.
- W2951061345 hasRelatedWork W2617544950 @default.
- W2951061345 hasRelatedWork W2803900643 @default.
- W2951061345 hasRelatedWork W284815315 @default.
- W2951061345 hasRelatedWork W2892242726 @default.
- W2951061345 hasRelatedWork W2898191801 @default.
- W2951061345 hasRelatedWork W2907941832 @default.
- W2951061345 hasRelatedWork W2910069423 @default.
- W2951061345 hasRelatedWork W2939844077 @default.
- W2951061345 hasRelatedWork W2942875436 @default.
- W2951061345 hasRelatedWork W2963834742 @default.
- W2951061345 hasRelatedWork W2979271689 @default.
- W2951061345 hasRelatedWork W3101818177 @default.
- W2951061345 hasRelatedWork W3121207335 @default.
- W2951061345 hasRelatedWork W3207964041 @default.
- W2951061345 hasRelatedWork W3208848212 @default.
- W2951061345 hasRelatedWork W2173965031 @default.
- W2951061345 hasRelatedWork W328998177 @default.
- W2951061345 isParatext "false" @default.
- W2951061345 isRetracted "false" @default.
- W2951061345 magId "2951061345" @default.
- W2951061345 workType "article" @default.