FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2617544950> ?p ?o ?g. }

• W2617544950 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.
• W2617544950 created "2017-06-05" @default.
• W2617544950 creator A5007668479 @default.
• W2617544950 creator A5021366411 @default.
• W2617544950 creator A5066294254 @default.
• W2617544950 date "2016-10-01" @default.
• W2617544950 modified "2023-09-27" @default.
• W2617544950 title "Biologically feasible deep learning with segregated dendrites" @default.
• W2617544950 cites W1520121841 @default.
• W2617544950 cites W1530897438 @default.
• W2617544950 cites W1645542202 @default.
• W2617544950 cites W1677182931 @default.
• W2617544950 cites W1853766545 @default.
• W2617544950 cites W1855112655 @default.
• W2617544950 cites W1987832351 @default.
• W2617544950 cites W1992910467 @default.
• W2617544950 cites W2003357516 @default.
• W2617544950 cites W2006814548 @default.
• W2617544950 cites W2040036684 @default.
• W2617544950 cites W2057613746 @default.
• W2617544950 cites W2061604397 @default.
• W2617544950 cites W2062967916 @default.
• W2617544950 cites W2089823661 @default.
• W2617544950 cites W2095705004 @default.
• W2617544950 cites W2101574677 @default.
• W2617544950 cites W2112796928 @default.
• W2617544950 cites W2123985235 @default.
• W2617544950 cites W2128420087 @default.
• W2617544950 cites W2136922672 @default.
• W2617544950 cites W2139022471 @default.
• W2617544950 cites W2140885691 @default.
• W2617544950 cites W2145339207 @default.
• W2617544950 cites W2153158097 @default.
• W2617544950 cites W2159110831 @default.
• W2617544950 cites W2163605009 @default.
• W2617544950 cites W2166138822 @default.
• W2617544950 cites W2166206801 @default.
• W2617544950 cites W2187089797 @default.
• W2617544950 cites W2190490644 @default.
• W2617544950 cites W2257979135 @default.
• W2617544950 cites W2274405424 @default.
• W2617544950 cites W2306521117 @default.
• W2617544950 cites W2343204383 @default.
• W2617544950 cites W2559385742 @default.
• W2617544950 cites W2919115771 @default.
• W2617544950 hasPublicationYear "2016" @default.
• W2617544950 type Work @default.
• W2617544950 sameAs 2617544950 @default.
• W2617544950 citedByCount "3" @default.
• W2617544950 countsByYear W26175449502019 @default.
• W2617544950 countsByYear W26175449502020 @default.
• W2617544950 crossrefType "posted-content" @default.
• W2617544950 hasAuthorship W2617544950A5007668479 @default.
• W2617544950 hasAuthorship W2617544950A5021366411 @default.
• W2617544950 hasAuthorship W2617544950A5066294254 @default.
• W2617544950 hasConcept C108583219 @default.
• W2617544950 hasConcept C152478114 @default.
• W2617544950 hasConcept C154945302 @default.
• W2617544950 hasConcept C169760540 @default.
• W2617544950 hasConcept C41008148 @default.
• W2617544950 hasConcept C50644808 @default.
• W2617544950 hasConcept C66949984 @default.
• W2617544950 hasConcept C86803240 @default.
• W2617544950 hasConcept C94124525 @default.
• W2617544950 hasConcept C94487597 @default.
• W2617544950 hasConceptScore W2617544950C108583219 @default.
• W2617544950 hasConceptScore W2617544950C152478114 @default.
• W2617544950 hasConceptScore W2617544950C154945302 @default.
• W2617544950 hasConceptScore W2617544950C169760540 @default.
• W2617544950 hasConceptScore W2617544950C41008148 @default.
• W2617544950 hasConceptScore W2617544950C50644808 @default.
• W2617544950 hasConceptScore W2617544950C66949984 @default.
• W2617544950 hasConceptScore W2617544950C86803240 @default.
• W2617544950 hasConceptScore W2617544950C94124525 @default.
• W2617544950 hasConceptScore W2617544950C94487597 @default.
• W2617544950 hasLocation W26175449501 @default.
• W2617544950 hasOpenAccess W2617544950 @default.
• W2617544950 hasPrimaryLocation W26175449501 @default.
• W2617544950 hasRelatedWork W1579411065 @default.
• W2617544950 hasRelatedWork W159324800 @default.
• W2617544950 hasRelatedWork W2222971467 @default.
• W2617544950 hasRelatedWork W2290481220 @default.
• W2617544950 hasRelatedWork W284815315 @default.
• W2617544950 hasRelatedWork W2892242726 @default.
• W2617544950 hasRelatedWork W2898191801 @default.
• W2617544950 hasRelatedWork W2907941832 @default.
• W2617544950 hasRelatedWork W2910069423 @default.
• W2617544950 hasRelatedWork W2939844077 @default.
• W2617544950 hasRelatedWork W2942875436 @default.
• W2617544950 hasRelatedWork W2951061345 @default.
• W2617544950 hasRelatedWork W2963834742 @default.
• W2617544950 hasRelatedWork W2979271689 @default.
• W2617544950 hasRelatedWork W2981052088 @default.
• W2617544950 hasRelatedWork W3101818177 @default.
• W2617544950 hasRelatedWork W3121207335 @default.
• W2617544950 hasRelatedWork W3207964041 @default.
• W2617544950 hasRelatedWork W3208848212 @default.
• W2617544950 hasRelatedWork W2173965031 @default.
• W2617544950 isParatext "false" @default.
• W2617544950 isRetracted "false" @default.

• next