Matches in SemOpenAlex for { <https://semopenalex.org/work/W2069630741> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2069630741 endingPage "612" @default.
- W2069630741 startingPage "601" @default.
- W2069630741 abstract "Dynamic recurrent neural networks composed of units with continuous activation functions provide a powerful tool for simulating a wide range of behaviors, since the requisite interconnections can be readily derived by gradient descent methods. However, it is not clear whether more realistic integrate-and-fire cells with comparable connection weights would perform the same functions. We therefore investigated methods to convert dynamic recurrent neural networks of continuous units into networks with integrate-and-fire cells. The transforms were tested on two recurrent networks derived by backpropagation. The first simulates a short-term memory task with units that mimic neural activity observed in cortex of monkeys performing instructed delay tasks. The network utilizes recurrent connections to generate sustained activity that codes the remembered value of a transient cue. The second network simulates patterns of neural activity observed in monkeys performing a step-tracking task with flexion/extension wrist movements. This more complicated network provides a working model of the interactions between multiple spinal and supraspinal centers controlling motoneurons. Our conversion algorithm replaced each continuous unit with multiple integrate-and-fire cells that interact through delayed synaptic potentials. Successful transformation depends on obtaining an appropriate fit between the activation function of the continuous units and the input-output relation of the spiking cells. This fit can be achieved by adapting the parameters of the synaptic potentials to replicate the input-output behavior of a standard sigmoidal activation function (shown for the short-term memory network). Alternatively, a customized activation function can be derived from the input-output relation of the spiking cells for a chosen set of parameters (demonstrated for the wrist flexion/extension network). In both cases the resulting networks of spiking cells exhibited activity that replicated the activity of corresponding continuous units. This confirms that the network solutions obtained through backpropagation apply to spiking networks and provides a useful method for deriving recurrent spiking networks performing a wide range of functions." @default.
- W2069630741 created "2016-06-24" @default.
- W2069630741 creator A5008021208 @default.
- W2069630741 creator A5030754436 @default.
- W2069630741 creator A5051313580 @default.
- W2069630741 date "2003-07-01" @default.
- W2069630741 modified "2023-10-16" @default.
- W2069630741 title "Recurrent neural networks of integrate-and-fire cells simulating short-term memory and wrist movement tasks derived from continuous dynamic networks" @default.
- W2069630741 cites W1553462100 @default.
- W2069630741 cites W1901661521 @default.
- W2069630741 cites W1975657359 @default.
- W2069630741 cites W1977608112 @default.
- W2069630741 cites W1986239264 @default.
- W2069630741 cites W1989512479 @default.
- W2069630741 cites W2003357516 @default.
- W2069630741 cites W2016589492 @default.
- W2069630741 cites W2031534534 @default.
- W2069630741 cites W2038321648 @default.
- W2069630741 cites W2110278466 @default.
- W2069630741 cites W2125253069 @default.
- W2069630741 cites W2129618392 @default.
- W2069630741 cites W2141290457 @default.
- W2069630741 cites W2153564253 @default.
- W2069630741 cites W2160361560 @default.
- W2069630741 cites W2168338665 @default.
- W2069630741 cites W2172294131 @default.
- W2069630741 cites W2204169799 @default.
- W2069630741 cites W2254263024 @default.
- W2069630741 cites W2271518742 @default.
- W2069630741 cites W2395981000 @default.
- W2069630741 cites W2407241542 @default.
- W2069630741 cites W2414606463 @default.
- W2069630741 cites W95059072 @default.
- W2069630741 doi "https://doi.org/10.1016/j.jphysparis.2004.01.017" @default.
- W2069630741 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/15242669" @default.
- W2069630741 hasPublicationYear "2003" @default.
- W2069630741 type Work @default.
- W2069630741 sameAs 2069630741 @default.
- W2069630741 citedByCount "5" @default.
- W2069630741 countsByYear W20696307412012 @default.
- W2069630741 countsByYear W20696307412019 @default.
- W2069630741 crossrefType "journal-article" @default.
- W2069630741 hasAuthorship W2069630741A5008021208 @default.
- W2069630741 hasAuthorship W2069630741A5030754436 @default.
- W2069630741 hasAuthorship W2069630741A5051313580 @default.
- W2069630741 hasConcept C121332964 @default.
- W2069630741 hasConcept C147168706 @default.
- W2069630741 hasConcept C154945302 @default.
- W2069630741 hasConcept C162324750 @default.
- W2069630741 hasConcept C187736073 @default.
- W2069630741 hasConcept C2780451532 @default.
- W2069630741 hasConcept C38365724 @default.
- W2069630741 hasConcept C41008148 @default.
- W2069630741 hasConcept C50644808 @default.
- W2069630741 hasConcept C61797465 @default.
- W2069630741 hasConcept C62520636 @default.
- W2069630741 hasConcept C81388566 @default.
- W2069630741 hasConceptScore W2069630741C121332964 @default.
- W2069630741 hasConceptScore W2069630741C147168706 @default.
- W2069630741 hasConceptScore W2069630741C154945302 @default.
- W2069630741 hasConceptScore W2069630741C162324750 @default.
- W2069630741 hasConceptScore W2069630741C187736073 @default.
- W2069630741 hasConceptScore W2069630741C2780451532 @default.
- W2069630741 hasConceptScore W2069630741C38365724 @default.
- W2069630741 hasConceptScore W2069630741C41008148 @default.
- W2069630741 hasConceptScore W2069630741C50644808 @default.
- W2069630741 hasConceptScore W2069630741C61797465 @default.
- W2069630741 hasConceptScore W2069630741C62520636 @default.
- W2069630741 hasConceptScore W2069630741C81388566 @default.
- W2069630741 hasIssue "4-6" @default.
- W2069630741 hasLocation W20696307411 @default.
- W2069630741 hasLocation W20696307412 @default.
- W2069630741 hasOpenAccess W2069630741 @default.
- W2069630741 hasPrimaryLocation W20696307411 @default.
- W2069630741 hasRelatedWork W1493495162 @default.
- W2069630741 hasRelatedWork W2076794896 @default.
- W2069630741 hasRelatedWork W2110328194 @default.
- W2069630741 hasRelatedWork W2115800717 @default.
- W2069630741 hasRelatedWork W2414384473 @default.
- W2069630741 hasRelatedWork W2986094345 @default.
- W2069630741 hasRelatedWork W3123157847 @default.
- W2069630741 hasRelatedWork W3170224572 @default.
- W2069630741 hasRelatedWork W3175461337 @default.
- W2069630741 hasRelatedWork W981675582 @default.
- W2069630741 hasVolume "97" @default.
- W2069630741 isParatext "false" @default.
- W2069630741 isRetracted "false" @default.
- W2069630741 magId "2069630741" @default.
- W2069630741 workType "article" @default.