Matches in SemOpenAlex for { <https://semopenalex.org/work/W2738720078> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2738720078 abstract "Deep learning has been successfully applied in several fields such as machine translation, manufacturing, and pattern recognition. However, successful application of deep learning depends upon appropriately setting its parameters to achieve high quality results. The number of hidden layers and the number of neurons in each layer of a deep machine learning network are two key parameters, which have main influence on the performance of the algorithm. Manual parameter setting and grid search approaches somewhat ease the users tasks in setting these important parameters. Nonetheless, these two techniques can be very time consuming. In this paper, we show that the Particle swarm optimization (PSO) technique holds great potential to optimize parameter settings and thus saves valuable computational resources during the tuning process of deep learning models. Specifically, we use a dataset collected from a Wi-Fi campus network to train deep learning models to predict the number of occupants and their locations. Our preliminary experiments indicate that PSO provides an efficient approach for tuning the optimal number of hidden layers and the number of neurons in each layer of the deep learning algorithm when compared to the grid search method. Our experiments illustrate that the exploration process of the landscape of configurations to find the optimal parameters is decreased by 77%-85%. In fact, the PSO yields even better accuracy results." @default.
- W2738720078 created "2017-07-31" @default.
- W2738720078 creator A5013564331 @default.
- W2738720078 creator A5028134056 @default.
- W2738720078 creator A5042094709 @default.
- W2738720078 creator A5052028161 @default.
- W2738720078 creator A5079814512 @default.
- W2738720078 date "2017-11-28" @default.
- W2738720078 modified "2023-09-27" @default.
- W2738720078 title "Parameters Optimization of Deep Learning Models using Particle Swarm Optimization" @default.
- W2738720078 hasPublicationYear "2017" @default.
- W2738720078 type Work @default.
- W2738720078 sameAs 2738720078 @default.
- W2738720078 citedByCount "0" @default.
- W2738720078 crossrefType "posted-content" @default.
- W2738720078 hasAuthorship W2738720078A5013564331 @default.
- W2738720078 hasAuthorship W2738720078A5028134056 @default.
- W2738720078 hasAuthorship W2738720078A5042094709 @default.
- W2738720078 hasAuthorship W2738720078A5052028161 @default.
- W2738720078 hasAuthorship W2738720078A5079814512 @default.
- W2738720078 hasConcept C10485038 @default.
- W2738720078 hasConcept C108583219 @default.
- W2738720078 hasConcept C111919701 @default.
- W2738720078 hasConcept C119857082 @default.
- W2738720078 hasConcept C12267149 @default.
- W2738720078 hasConcept C154945302 @default.
- W2738720078 hasConcept C178790620 @default.
- W2738720078 hasConcept C185592680 @default.
- W2738720078 hasConcept C187691185 @default.
- W2738720078 hasConcept C2524010 @default.
- W2738720078 hasConcept C26517878 @default.
- W2738720078 hasConcept C2779227376 @default.
- W2738720078 hasConcept C33923547 @default.
- W2738720078 hasConcept C38652104 @default.
- W2738720078 hasConcept C41008148 @default.
- W2738720078 hasConcept C85617194 @default.
- W2738720078 hasConcept C97385483 @default.
- W2738720078 hasConcept C98045186 @default.
- W2738720078 hasConceptScore W2738720078C10485038 @default.
- W2738720078 hasConceptScore W2738720078C108583219 @default.
- W2738720078 hasConceptScore W2738720078C111919701 @default.
- W2738720078 hasConceptScore W2738720078C119857082 @default.
- W2738720078 hasConceptScore W2738720078C12267149 @default.
- W2738720078 hasConceptScore W2738720078C154945302 @default.
- W2738720078 hasConceptScore W2738720078C178790620 @default.
- W2738720078 hasConceptScore W2738720078C185592680 @default.
- W2738720078 hasConceptScore W2738720078C187691185 @default.
- W2738720078 hasConceptScore W2738720078C2524010 @default.
- W2738720078 hasConceptScore W2738720078C26517878 @default.
- W2738720078 hasConceptScore W2738720078C2779227376 @default.
- W2738720078 hasConceptScore W2738720078C33923547 @default.
- W2738720078 hasConceptScore W2738720078C38652104 @default.
- W2738720078 hasConceptScore W2738720078C41008148 @default.
- W2738720078 hasConceptScore W2738720078C85617194 @default.
- W2738720078 hasConceptScore W2738720078C97385483 @default.
- W2738720078 hasConceptScore W2738720078C98045186 @default.
- W2738720078 hasLocation W27387200781 @default.
- W2738720078 hasOpenAccess W2738720078 @default.
- W2738720078 hasPrimaryLocation W27387200781 @default.
- W2738720078 hasRelatedWork W120971688 @default.
- W2738720078 hasRelatedWork W1606456968 @default.
- W2738720078 hasRelatedWork W1631708156 @default.
- W2738720078 hasRelatedWork W2084627971 @default.
- W2738720078 hasRelatedWork W2617308160 @default.
- W2738720078 hasRelatedWork W2767224631 @default.
- W2738720078 hasRelatedWork W2810206120 @default.
- W2738720078 hasRelatedWork W2913905342 @default.
- W2738720078 hasRelatedWork W3006105210 @default.
- W2738720078 hasRelatedWork W3008275213 @default.
- W2738720078 hasRelatedWork W3016539020 @default.
- W2738720078 hasRelatedWork W3022987990 @default.
- W2738720078 hasRelatedWork W3102888966 @default.
- W2738720078 hasRelatedWork W3103370507 @default.
- W2738720078 hasRelatedWork W3134587287 @default.
- W2738720078 hasRelatedWork W3178802061 @default.
- W2738720078 hasRelatedWork W3190982209 @default.
- W2738720078 hasRelatedWork W3191950921 @default.
- W2738720078 hasRelatedWork W3194671788 @default.
- W2738720078 hasRelatedWork W3199451380 @default.
- W2738720078 isParatext "false" @default.
- W2738720078 isRetracted "false" @default.
- W2738720078 magId "2738720078" @default.
- W2738720078 workType "article" @default.