Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384158657> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4384158657 abstract "Artificial intelligence makes significant progress attributing to the deep learning adopting neurophysiological strategies. The learning process in deep learning is resemble to that in the brain. However, the traditional nodes with a uniform structure form are much simpler than the biological neurons with branches in the brain. To investigate whether realistic neurons with multi-compartment structures could optimize the deep learning algorithm, a three-layer deep learning network with multi-compartment neurons is designed. The results show that three-compartment neuronal structure with apical dendrites makes the network perform a better learning effect compared with the two-compartment and single-compartment neuronal structure on coding MNIST database. The apical dendrites separate the feedforward and feedback signals, which provides a way for solving credit assignment problem. In addition, the introduction of apical dendrites increases the correlation between the loss of hidden and output layers. The effect of axial conductance from the apical dendrite to soma and the conductance related to spike frequency adaptation (SFA) current is quantified. The results show that greater axial conductance generates higher accuracy. And the adaptation conductance reaches the highest accuracy at around 97.2% when the interval is in 1mS/cm <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> ~3.4mS/cm <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> . This work contributes to a better understanding of the function of multi-compartment structure in deep learning algorithms and provides insight into constructing a deep learning network with biophysical characteristics." @default.
- W4384158657 created "2023-07-14" @default.
- W4384158657 creator A5003360183 @default.
- W4384158657 creator A5021452379 @default.
- W4384158657 creator A5027108181 @default.
- W4384158657 creator A5038741227 @default.
- W4384158657 creator A5040071083 @default.
- W4384158657 creator A5063578134 @default.
- W4384158657 creator A5092460782 @default.
- W4384158657 date "2023-05-22" @default.
- W4384158657 modified "2023-10-16" @default.
- W4384158657 title "Multi-compartment structure optimizes the deep learning network from the biophysical perspective" @default.
- W4384158657 cites W1526741802 @default.
- W4384158657 cites W1576838367 @default.
- W4384158657 cites W2040036684 @default.
- W4384158657 cites W2139022471 @default.
- W4384158657 cites W2159217888 @default.
- W4384158657 cites W2166206801 @default.
- W4384158657 cites W2274405424 @default.
- W4384158657 cites W2343204383 @default.
- W4384158657 cites W2529004582 @default.
- W4384158657 cites W2753797385 @default.
- W4384158657 cites W2883249177 @default.
- W4384158657 cites W2963504849 @default.
- W4384158657 cites W3042391950 @default.
- W4384158657 cites W4207058902 @default.
- W4384158657 cites W4234546939 @default.
- W4384158657 cites W4283726157 @default.
- W4384158657 doi "https://doi.org/10.1109/i2mtc53148.2023.10176048" @default.
- W4384158657 hasPublicationYear "2023" @default.
- W4384158657 type Work @default.
- W4384158657 citedByCount "0" @default.
- W4384158657 crossrefType "proceedings-article" @default.
- W4384158657 hasAuthorship W4384158657A5003360183 @default.
- W4384158657 hasAuthorship W4384158657A5021452379 @default.
- W4384158657 hasAuthorship W4384158657A5027108181 @default.
- W4384158657 hasAuthorship W4384158657A5038741227 @default.
- W4384158657 hasAuthorship W4384158657A5040071083 @default.
- W4384158657 hasAuthorship W4384158657A5063578134 @default.
- W4384158657 hasAuthorship W4384158657A5092460782 @default.
- W4384158657 hasConcept C108583219 @default.
- W4384158657 hasConcept C111368507 @default.
- W4384158657 hasConcept C11413529 @default.
- W4384158657 hasConcept C114614502 @default.
- W4384158657 hasConcept C121332964 @default.
- W4384158657 hasConcept C121932024 @default.
- W4384158657 hasConcept C127313418 @default.
- W4384158657 hasConcept C152478114 @default.
- W4384158657 hasConcept C154945302 @default.
- W4384158657 hasConcept C169760540 @default.
- W4384158657 hasConcept C186060115 @default.
- W4384158657 hasConcept C190502265 @default.
- W4384158657 hasConcept C203635412 @default.
- W4384158657 hasConcept C2779617337 @default.
- W4384158657 hasConcept C33923547 @default.
- W4384158657 hasConcept C41008148 @default.
- W4384158657 hasConcept C86803240 @default.
- W4384158657 hasConceptScore W4384158657C108583219 @default.
- W4384158657 hasConceptScore W4384158657C111368507 @default.
- W4384158657 hasConceptScore W4384158657C11413529 @default.
- W4384158657 hasConceptScore W4384158657C114614502 @default.
- W4384158657 hasConceptScore W4384158657C121332964 @default.
- W4384158657 hasConceptScore W4384158657C121932024 @default.
- W4384158657 hasConceptScore W4384158657C127313418 @default.
- W4384158657 hasConceptScore W4384158657C152478114 @default.
- W4384158657 hasConceptScore W4384158657C154945302 @default.
- W4384158657 hasConceptScore W4384158657C169760540 @default.
- W4384158657 hasConceptScore W4384158657C186060115 @default.
- W4384158657 hasConceptScore W4384158657C190502265 @default.
- W4384158657 hasConceptScore W4384158657C203635412 @default.
- W4384158657 hasConceptScore W4384158657C2779617337 @default.
- W4384158657 hasConceptScore W4384158657C33923547 @default.
- W4384158657 hasConceptScore W4384158657C41008148 @default.
- W4384158657 hasConceptScore W4384158657C86803240 @default.
- W4384158657 hasFunder F4320321001 @default.
- W4384158657 hasLocation W43841586571 @default.
- W4384158657 hasOpenAccess W4384158657 @default.
- W4384158657 hasPrimaryLocation W43841586571 @default.
- W4384158657 hasRelatedWork W2167735388 @default.
- W4384158657 hasRelatedWork W2276478028 @default.
- W4384158657 hasRelatedWork W2787767549 @default.
- W4384158657 hasRelatedWork W2892911634 @default.
- W4384158657 hasRelatedWork W2904174853 @default.
- W4384158657 hasRelatedWork W2947175736 @default.
- W4384158657 hasRelatedWork W3156786002 @default.
- W4384158657 hasRelatedWork W4220697888 @default.
- W4384158657 hasRelatedWork W4287510235 @default.
- W4384158657 hasRelatedWork W4309224979 @default.
- W4384158657 isParatext "false" @default.
- W4384158657 isRetracted "false" @default.
- W4384158657 workType "article" @default.