Matches in SemOpenAlex for { <https://semopenalex.org/work/W2201721810> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2201721810 endingPage "1924" @default.
- W2201721810 startingPage "1915" @default.
- W2201721810 abstract "Deep neural networks are a branch in machine learning that has seen a meteoric rise in popularity due to its powerful abilities to represent and model high-level abstractions in highly complex data. One area in deep neural networks that are ripe for exploration is neural connectivity formation. A pivotal study on the brain tissue of rats found that synaptic formation for specific functional connectivity in neocortical neural microcircuits can be surprisingly well modeled and predicted as a random formation. Motivated by this intriguing finding, we introduce the concept of StochasticNet where deep neural networks are formed via stochastic connectivity between neurons. As a result, any type of deep neural networks can be formed as a StochasticNet by allowing the neuron connectivity to be stochastic. Stochastic synaptic formations in a deep neural network architecture can allow for efficient utilization of neurons for performing specific tasks. To evaluate the feasibility of such a deep neural network architecture, we train a StochasticNet using four different image datasets (CIFAR-10, MNIST, SVHN, and STL-10). Experimental results show that a StochasticNet using less than half the number of neural connections as a conventional deep neural network achieves comparable accuracy and reduces overfitting on the CIFAR-10, MNIST, and SVHN data sets. Interestingly, StochasticNet with less than half the number of neural connections, achieved a higher accuracy (relative improvement in test error rate of ~6% compared to ConvNet) on the STL-10 data set than a conventional deep neural network. Finally, the StochasticNets have faster operational speeds while achieving better or similar accuracy performances." @default.
- W2201721810 created "2016-06-24" @default.
- W2201721810 creator A5023861925 @default.
- W2201721810 creator A5034161060 @default.
- W2201721810 creator A5040284711 @default.
- W2201721810 date "2016-01-01" @default.
- W2201721810 modified "2023-10-17" @default.
- W2201721810 title "StochasticNet: Forming Deep Neural Networks via Stochastic Connectivity" @default.
- W2201721810 cites W1677182931 @default.
- W2201721810 cites W1963882359 @default.
- W2201721810 cites W2072089154 @default.
- W2201721810 cites W2104636679 @default.
- W2201721810 cites W2109255472 @default.
- W2201721810 cites W2112796928 @default.
- W2201721810 cites W2117130368 @default.
- W2201721810 cites W2134557905 @default.
- W2201721810 cites W2147768505 @default.
- W2201721810 cites W4252973173 @default.
- W2201721810 cites W4312512934 @default.
- W2201721810 doi "https://doi.org/10.1109/access.2016.2551458" @default.
- W2201721810 hasPublicationYear "2016" @default.
- W2201721810 type Work @default.
- W2201721810 sameAs 2201721810 @default.
- W2201721810 citedByCount "28" @default.
- W2201721810 countsByYear W22017218102015 @default.
- W2201721810 countsByYear W22017218102016 @default.
- W2201721810 countsByYear W22017218102017 @default.
- W2201721810 countsByYear W22017218102018 @default.
- W2201721810 countsByYear W22017218102019 @default.
- W2201721810 countsByYear W22017218102020 @default.
- W2201721810 countsByYear W22017218102021 @default.
- W2201721810 countsByYear W22017218102022 @default.
- W2201721810 countsByYear W22017218102023 @default.
- W2201721810 crossrefType "journal-article" @default.
- W2201721810 hasAuthorship W2201721810A5023861925 @default.
- W2201721810 hasAuthorship W2201721810A5034161060 @default.
- W2201721810 hasAuthorship W2201721810A5040284711 @default.
- W2201721810 hasBestOaLocation W22017218101 @default.
- W2201721810 hasConcept C108583219 @default.
- W2201721810 hasConcept C119857082 @default.
- W2201721810 hasConcept C147168706 @default.
- W2201721810 hasConcept C153180895 @default.
- W2201721810 hasConcept C154945302 @default.
- W2201721810 hasConcept C190502265 @default.
- W2201721810 hasConcept C206688291 @default.
- W2201721810 hasConcept C22019652 @default.
- W2201721810 hasConcept C2984842247 @default.
- W2201721810 hasConcept C41008148 @default.
- W2201721810 hasConcept C50644808 @default.
- W2201721810 hasConcept C86582703 @default.
- W2201721810 hasConceptScore W2201721810C108583219 @default.
- W2201721810 hasConceptScore W2201721810C119857082 @default.
- W2201721810 hasConceptScore W2201721810C147168706 @default.
- W2201721810 hasConceptScore W2201721810C153180895 @default.
- W2201721810 hasConceptScore W2201721810C154945302 @default.
- W2201721810 hasConceptScore W2201721810C190502265 @default.
- W2201721810 hasConceptScore W2201721810C206688291 @default.
- W2201721810 hasConceptScore W2201721810C22019652 @default.
- W2201721810 hasConceptScore W2201721810C2984842247 @default.
- W2201721810 hasConceptScore W2201721810C41008148 @default.
- W2201721810 hasConceptScore W2201721810C50644808 @default.
- W2201721810 hasConceptScore W2201721810C86582703 @default.
- W2201721810 hasFunder F4320321886 @default.
- W2201721810 hasLocation W22017218101 @default.
- W2201721810 hasLocation W22017218102 @default.
- W2201721810 hasOpenAccess W2201721810 @default.
- W2201721810 hasPrimaryLocation W22017218101 @default.
- W2201721810 hasRelatedWork W2618574054 @default.
- W2201721810 hasRelatedWork W2786764570 @default.
- W2201721810 hasRelatedWork W2937906318 @default.
- W2201721810 hasRelatedWork W2987302549 @default.
- W2201721810 hasRelatedWork W3015792155 @default.
- W2201721810 hasRelatedWork W3095450733 @default.
- W2201721810 hasRelatedWork W3118286710 @default.
- W2201721810 hasRelatedWork W4225929918 @default.
- W2201721810 hasRelatedWork W4315785049 @default.
- W2201721810 hasRelatedWork W4385524141 @default.
- W2201721810 hasVolume "4" @default.
- W2201721810 isParatext "false" @default.
- W2201721810 isRetracted "false" @default.
- W2201721810 magId "2201721810" @default.
- W2201721810 workType "article" @default.