Modified Convolutional Neural Network Based on Dropout and the Stochastic Gradient Descent Optimizer

Modified Convolutional Neural Network Based on Dropout and the Stochastic Gradient Descent Optimizer

This study proposes a modified convolutional neural network (CNN) algorithm that is based on dropout and the stochastic gradient descent (SGD) optimizer (MCNN-DS), after analyzing the problems of CNNs in extracting the convolution features, to improve the feature recognition rate and reduce the time...

Full description

Bibliographic Details
Main Authors: Jing Yang, Guanci Yang
Format: Article
Language:English
Published: MDPI AG 2018-03-01
Series:Algorithms
Subjects:
convolutional neural network
activate function
dropout
SGD optimizer
Online Access:http://www.mdpi.com/1999-4893/11/3/28

Similar Items

Similar Items