Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003893721> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3003893721 startingPage "31" @default.
- W3003893721 abstract "We study input compression in a biologically inspired model of neural computation. We demonstrate that a network consisting of a random projection step (implemented via random synaptic connectivity) followed by a sparsification step (implemented via winner-take-all competition) can reduce well-separated high-dimensional input vectors to well-separated low-dimensional vectors. By augmenting our network with a third module, we can efficiently map each input (along with any small perturbations of the input) to a unique representative neuron, solving a neural clustering problem.Both the size of our network and its processing time, i.e., the time it takes the network to compute the compressed output given a presented input, are independent of the (potentially large) dimension of the input patterns and depend only on the number of distinct inputs that the network must encode and the pairwise relative Hamming distance between these inputs. The first two steps of our construction mirror known biological networks, for example, in the fruit fly olfactory system [Caron et al., 2013; Lin et al., 2014; Dasgupta et al., 2017]. Our analysis helps provide a theoretical understanding of these networks and lay a foundation for how random compression and input memorization may be implemented in biological neural networks.Technically, a contribution in our network design is the implementation of a short-term memory. Our network can be given a desired memory time t_m as an input parameter and satisfies the following with high probability: any pattern presented several times within a time window of t_m rounds will be mapped to a single representative output neuron. However, a pattern not presented for c⋅t_m rounds for some constant c>1 will be forgotten, and its representative output neuron will be released, to accommodate newly introduced patterns." @default.
- W3003893721 created "2020-02-07" @default.
- W3003893721 creator A5022875077 @default.
- W3003893721 creator A5023229845 @default.
- W3003893721 creator A5044915753 @default.
- W3003893721 creator A5071944803 @default.
- W3003893721 date "2020-01-01" @default.
- W3003893721 modified "2023-09-23" @default.
- W3003893721 title "Random Sketching, Clustering, and Short-Term Memory in Spiking Neural Networks." @default.
- W3003893721 doi "https://doi.org/10.4230/lipics.itcs.2020.23" @default.
- W3003893721 hasPublicationYear "2020" @default.
- W3003893721 type Work @default.
- W3003893721 sameAs 3003893721 @default.
- W3003893721 citedByCount "3" @default.
- W3003893721 countsByYear W30038937212019 @default.
- W3003893721 countsByYear W30038937212020 @default.
- W3003893721 countsByYear W30038937212021 @default.
- W3003893721 crossrefType "proceedings-article" @default.
- W3003893721 hasAuthorship W3003893721A5022875077 @default.
- W3003893721 hasAuthorship W3003893721A5023229845 @default.
- W3003893721 hasAuthorship W3003893721A5044915753 @default.
- W3003893721 hasAuthorship W3003893721A5071944803 @default.
- W3003893721 hasConcept C11413529 @default.
- W3003893721 hasConcept C11731999 @default.
- W3003893721 hasConcept C154945302 @default.
- W3003893721 hasConcept C193319292 @default.
- W3003893721 hasConcept C2777036070 @default.
- W3003893721 hasConcept C33010914 @default.
- W3003893721 hasConcept C41008148 @default.
- W3003893721 hasConcept C50644808 @default.
- W3003893721 hasConcept C73555534 @default.
- W3003893721 hasConcept C80444323 @default.
- W3003893721 hasConceptScore W3003893721C11413529 @default.
- W3003893721 hasConceptScore W3003893721C11731999 @default.
- W3003893721 hasConceptScore W3003893721C154945302 @default.
- W3003893721 hasConceptScore W3003893721C193319292 @default.
- W3003893721 hasConceptScore W3003893721C2777036070 @default.
- W3003893721 hasConceptScore W3003893721C33010914 @default.
- W3003893721 hasConceptScore W3003893721C41008148 @default.
- W3003893721 hasConceptScore W3003893721C50644808 @default.
- W3003893721 hasConceptScore W3003893721C73555534 @default.
- W3003893721 hasConceptScore W3003893721C80444323 @default.
- W3003893721 hasLocation W30038937211 @default.
- W3003893721 hasOpenAccess W3003893721 @default.
- W3003893721 hasPrimaryLocation W30038937211 @default.
- W3003893721 hasRelatedWork W141558020 @default.
- W3003893721 hasRelatedWork W1550736670 @default.
- W3003893721 hasRelatedWork W1992054976 @default.
- W3003893721 hasRelatedWork W1995011385 @default.
- W3003893721 hasRelatedWork W2019633842 @default.
- W3003893721 hasRelatedWork W2063370617 @default.
- W3003893721 hasRelatedWork W2078762882 @default.
- W3003893721 hasRelatedWork W2130663964 @default.
- W3003893721 hasRelatedWork W2181382924 @default.
- W3003893721 hasRelatedWork W2305996987 @default.
- W3003893721 hasRelatedWork W2461336877 @default.
- W3003893721 hasRelatedWork W2561054127 @default.
- W3003893721 hasRelatedWork W2892830725 @default.
- W3003893721 hasRelatedWork W2981710180 @default.
- W3003893721 hasRelatedWork W2990498047 @default.
- W3003893721 hasRelatedWork W3004565269 @default.
- W3003893721 hasRelatedWork W3049639017 @default.
- W3003893721 hasRelatedWork W3122138730 @default.
- W3003893721 hasRelatedWork W3200692463 @default.
- W3003893721 hasRelatedWork W2125217644 @default.
- W3003893721 isParatext "false" @default.
- W3003893721 isRetracted "false" @default.
- W3003893721 magId "3003893721" @default.
- W3003893721 workType "article" @default.