Matches in SemOpenAlex for { <https://semopenalex.org/work/W3189227003> ?p ?o ?g. }
- W3189227003 endingPage "e1009202" @default.
- W3189227003 startingPage "e1009202" @default.
- W3189227003 abstract "Artificial neural networks, taking inspiration from biological neurons, have become an invaluable tool for machine learning applications. Recent studies have developed techniques to effectively tune the connectivity of sparsely-connected artificial neural networks, which have the potential to be more computationally efficient than their fully-connected counterparts and more closely resemble the architectures of biological systems. We here present a normalisation, based on the biophysical behaviour of neuronal dendrites receiving distributed synaptic inputs, that divides the weight of an artificial neuron’s afferent contacts by their number. We apply this dendritic normalisation to various sparsely-connected feedforward network architectures, as well as simple recurrent and self-organised networks with spatially extended units. The learning performance is significantly increased, providing an improvement over other widely-used normalisations in sparse networks. The results are two-fold, being both a practical advance in machine learning and an insight into how the structure of neuronal dendritic arbours may contribute to computation." @default.
- W3189227003 created "2021-08-16" @default.
- W3189227003 creator A5046801422 @default.
- W3189227003 creator A5059626898 @default.
- W3189227003 creator A5087445451 @default.
- W3189227003 date "2021-08-09" @default.
- W3189227003 modified "2023-10-12" @default.
- W3189227003 title "Dendritic normalisation improves learning in sparsely connected artificial neural networks" @default.
- W3189227003 cites W101771737 @default.
- W3189227003 cites W1489333352 @default.
- W3189227003 cites W1498436455 @default.
- W3189227003 cites W1504248943 @default.
- W3189227003 cites W1965210407 @default.
- W3189227003 cites W1979854415 @default.
- W3189227003 cites W1991762922 @default.
- W3189227003 cites W1994616650 @default.
- W3189227003 cites W1995341919 @default.
- W3189227003 cites W1998324420 @default.
- W3189227003 cites W2004921550 @default.
- W3189227003 cites W2015701831 @default.
- W3189227003 cites W2020587316 @default.
- W3189227003 cites W2031477181 @default.
- W3189227003 cites W2057613746 @default.
- W3189227003 cites W2059994748 @default.
- W3189227003 cites W2076148352 @default.
- W3189227003 cites W2095202445 @default.
- W3189227003 cites W2103744641 @default.
- W3189227003 cites W2111935653 @default.
- W3189227003 cites W2112796928 @default.
- W3189227003 cites W2115831804 @default.
- W3189227003 cites W2134864228 @default.
- W3189227003 cites W2141125852 @default.
- W3189227003 cites W2147800946 @default.
- W3189227003 cites W2164649534 @default.
- W3189227003 cites W2166247014 @default.
- W3189227003 cites W2230946642 @default.
- W3189227003 cites W2285155087 @default.
- W3189227003 cites W2290982066 @default.
- W3189227003 cites W2347205908 @default.
- W3189227003 cites W2432567885 @default.
- W3189227003 cites W2511999769 @default.
- W3189227003 cites W2560647685 @default.
- W3189227003 cites W2801400980 @default.
- W3189227003 cites W2888326090 @default.
- W3189227003 cites W2946185430 @default.
- W3189227003 cites W2962683355 @default.
- W3189227003 cites W2978368159 @default.
- W3189227003 cites W2998412226 @default.
- W3189227003 cites W3016391357 @default.
- W3189227003 cites W3041043806 @default.
- W3189227003 cites W3043133474 @default.
- W3189227003 cites W3093082364 @default.
- W3189227003 cites W3101584733 @default.
- W3189227003 cites W4212952892 @default.
- W3189227003 doi "https://doi.org/10.1371/journal.pcbi.1009202" @default.
- W3189227003 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8407571" @default.
- W3189227003 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34370727" @default.
- W3189227003 hasPublicationYear "2021" @default.
- W3189227003 type Work @default.
- W3189227003 sameAs 3189227003 @default.
- W3189227003 citedByCount "6" @default.
- W3189227003 countsByYear W31892270032021 @default.
- W3189227003 countsByYear W31892270032022 @default.
- W3189227003 countsByYear W31892270032023 @default.
- W3189227003 crossrefType "journal-article" @default.
- W3189227003 hasAuthorship W3189227003A5046801422 @default.
- W3189227003 hasAuthorship W3189227003A5059626898 @default.
- W3189227003 hasAuthorship W3189227003A5087445451 @default.
- W3189227003 hasBestOaLocation W31892270031 @default.
- W3189227003 hasConcept C108583219 @default.
- W3189227003 hasConcept C119857082 @default.
- W3189227003 hasConcept C127413603 @default.
- W3189227003 hasConcept C133731056 @default.
- W3189227003 hasConcept C147168706 @default.
- W3189227003 hasConcept C154945302 @default.
- W3189227003 hasConcept C173079777 @default.
- W3189227003 hasConcept C177973122 @default.
- W3189227003 hasConcept C28225019 @default.
- W3189227003 hasConcept C33766855 @default.
- W3189227003 hasConcept C38858127 @default.
- W3189227003 hasConcept C41008148 @default.
- W3189227003 hasConcept C50644808 @default.
- W3189227003 hasConcept C60644358 @default.
- W3189227003 hasConcept C86803240 @default.
- W3189227003 hasConceptScore W3189227003C108583219 @default.
- W3189227003 hasConceptScore W3189227003C119857082 @default.
- W3189227003 hasConceptScore W3189227003C127413603 @default.
- W3189227003 hasConceptScore W3189227003C133731056 @default.
- W3189227003 hasConceptScore W3189227003C147168706 @default.
- W3189227003 hasConceptScore W3189227003C154945302 @default.
- W3189227003 hasConceptScore W3189227003C173079777 @default.
- W3189227003 hasConceptScore W3189227003C177973122 @default.
- W3189227003 hasConceptScore W3189227003C28225019 @default.
- W3189227003 hasConceptScore W3189227003C33766855 @default.
- W3189227003 hasConceptScore W3189227003C38858127 @default.
- W3189227003 hasConceptScore W3189227003C41008148 @default.
- W3189227003 hasConceptScore W3189227003C50644808 @default.
- W3189227003 hasConceptScore W3189227003C60644358 @default.