Matches in SemOpenAlex for { <https://semopenalex.org/work/W2288304434> ?p ?o ?g. }
- W2288304434 endingPage "752" @default.
- W2288304434 startingPage "743" @default.
- W2288304434 abstract "When designing neural networks for tackling hard classification problems researchers face the trivial problem of deciding the appropriate size of the neural network. The problem of optimizing the size of a neural network for obtaining high classification accuracy in datasets is indeed a hard problem in the literature. Existing studies provide theoretical upper bounds on the size of neural networks that are unrealistic to implement. Alternatively, optimizing empirically the neural network size may need a large number of experiments, which due to a considerable number of free parameters may become a real hard task in time and effort to accomplish. Hard classification problems are usually large in size datasets. Such datasets derive from collection of real world data like from multimedia content and are usually rich in training samples and rich in features that describe each collected sample. Working with neural networks and hard classification datasets will make even harder the task to optimize the neural network size. This work highlights on a mathematical formula for a priori calculating the size of a neural network for achieving high classification accuracy rate. The formula estimates neural networks size based only on the number of available training samples, resulting in sizes of neural networks that are realistic to implement. Using this formula in hard classification datasets aims to fix the size of an accurate neural network and allows researchers to concentrate on other aspects of their experiments. The focus on this approach turns to the number of available data for training the neural network, which is a new perspective in the neural network theory and the characteristics of this perspective are discussed in this article for designing neural networks for tackling hard classification problems." @default.
- W2288304434 created "2016-06-24" @default.
- W2288304434 creator A5065636977 @default.
- W2288304434 date "2009-06-01" @default.
- W2288304434 modified "2023-09-23" @default.
- W2288304434 title "Designing neural networks for tackling hard classification problems" @default.
- W2288304434 cites W113574153 @default.
- W2288304434 cites W1493142224 @default.
- W2288304434 cites W1495176091 @default.
- W2288304434 cites W1508080521 @default.
- W2288304434 cites W1541778944 @default.
- W2288304434 cites W158238498 @default.
- W2288304434 cites W1583772825 @default.
- W2288304434 cites W1620637521 @default.
- W2288304434 cites W1649899421 @default.
- W2288304434 cites W1744207076 @default.
- W2288304434 cites W196871588 @default.
- W2288304434 cites W1969557815 @default.
- W2288304434 cites W1984424319 @default.
- W2288304434 cites W1993224830 @default.
- W2288304434 cites W1995341919 @default.
- W2288304434 cites W2005228957 @default.
- W2288304434 cites W2006698588 @default.
- W2288304434 cites W2008279136 @default.
- W2288304434 cites W2011956661 @default.
- W2288304434 cites W2012903341 @default.
- W2288304434 cites W2019671617 @default.
- W2288304434 cites W2024195378 @default.
- W2288304434 cites W2029538739 @default.
- W2288304434 cites W2033500239 @default.
- W2288304434 cites W2041334099 @default.
- W2288304434 cites W2046907549 @default.
- W2288304434 cites W2050946712 @default.
- W2288304434 cites W2066915075 @default.
- W2288304434 cites W2090398894 @default.
- W2288304434 cites W2099579348 @default.
- W2288304434 cites W2115881141 @default.
- W2288304434 cites W2129178713 @default.
- W2288304434 cites W2141630781 @default.
- W2288304434 cites W2150588589 @default.
- W2288304434 cites W2151554678 @default.
- W2288304434 cites W2156260858 @default.
- W2288304434 cites W2165758113 @default.
- W2288304434 cites W2281635658 @default.
- W2288304434 cites W2322002063 @default.
- W2288304434 cites W2490905019 @default.
- W2288304434 cites W2597999290 @default.
- W2288304434 cites W2792468650 @default.
- W2288304434 cites W2799061466 @default.
- W2288304434 cites W41660157 @default.
- W2288304434 cites W53847646 @default.
- W2288304434 cites W92982764 @default.
- W2288304434 cites W2165025072 @default.
- W2288304434 hasPublicationYear "2009" @default.
- W2288304434 type Work @default.
- W2288304434 sameAs 2288304434 @default.
- W2288304434 citedByCount "1" @default.
- W2288304434 crossrefType "journal-article" @default.
- W2288304434 hasAuthorship W2288304434A5065636977 @default.
- W2288304434 hasConcept C105795698 @default.
- W2288304434 hasConcept C111472728 @default.
- W2288304434 hasConcept C119857082 @default.
- W2288304434 hasConcept C124101348 @default.
- W2288304434 hasConcept C127413603 @default.
- W2288304434 hasConcept C129848803 @default.
- W2288304434 hasConcept C138885662 @default.
- W2288304434 hasConcept C144024400 @default.
- W2288304434 hasConcept C154945302 @default.
- W2288304434 hasConcept C201995342 @default.
- W2288304434 hasConcept C2779304628 @default.
- W2288304434 hasConcept C2780451532 @default.
- W2288304434 hasConcept C33923547 @default.
- W2288304434 hasConcept C36289849 @default.
- W2288304434 hasConcept C41008148 @default.
- W2288304434 hasConcept C50644808 @default.
- W2288304434 hasConcept C75553542 @default.
- W2288304434 hasConceptScore W2288304434C105795698 @default.
- W2288304434 hasConceptScore W2288304434C111472728 @default.
- W2288304434 hasConceptScore W2288304434C119857082 @default.
- W2288304434 hasConceptScore W2288304434C124101348 @default.
- W2288304434 hasConceptScore W2288304434C127413603 @default.
- W2288304434 hasConceptScore W2288304434C129848803 @default.
- W2288304434 hasConceptScore W2288304434C138885662 @default.
- W2288304434 hasConceptScore W2288304434C144024400 @default.
- W2288304434 hasConceptScore W2288304434C154945302 @default.
- W2288304434 hasConceptScore W2288304434C201995342 @default.
- W2288304434 hasConceptScore W2288304434C2779304628 @default.
- W2288304434 hasConceptScore W2288304434C2780451532 @default.
- W2288304434 hasConceptScore W2288304434C33923547 @default.
- W2288304434 hasConceptScore W2288304434C36289849 @default.
- W2288304434 hasConceptScore W2288304434C41008148 @default.
- W2288304434 hasConceptScore W2288304434C50644808 @default.
- W2288304434 hasConceptScore W2288304434C75553542 @default.
- W2288304434 hasIssue "6" @default.
- W2288304434 hasLocation W22883044341 @default.
- W2288304434 hasOpenAccess W2288304434 @default.
- W2288304434 hasPrimaryLocation W22883044341 @default.
- W2288304434 hasRelatedWork W123635158 @default.