publication . Article . 2017

Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets

Vadim Romanuke;
Open Access English
  • Published: 01 Dec 2017 Journal: Applied Computer Systems (issn: 2255-8691, Copyright policy)
  • Publisher: Sciendo
Abstract
<jats:title>Abstract</jats:title> <jats:p>A technique of DropOut for preventing overfitting of convolutional neural networks for image classification is considered in the paper. The goal is to find a rule of rationally allocating DropOut layers of 0.5 rate to maximise performance. To achieve the goal, two common network architectures are used having either 4 or 5 convolutional layers. Benchmarking is fulfilled with CIFAR-10, EEACL26, and NORB datasets. Initially, series of all admissible versions for allocation of DropOut layers are generated. After the performance against the series is evaluated, normalized and averaged, the compromising rule is found. It consi...
Subjects
free text keywords: CIFAR-10, convolutional neural network, DropOut, EEACL26, image classification, NORB, overfitting, Computer software, QA76.75-76.765
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue