A Model of Deep Neural Network for Iris Classification With Different Activation Functions

In recent years, deep neural network (DNN) has been frequently used for classification. In this study, iris flowers having 3 different types are classified by using DNN which are utilized the width and length of petal and sepal features as input. Some experiments are made for the iris dataset by usi...

Full description

Saved in:
Bibliographic Details
Published in2018 International Conference on Artificial Intelligence and Data Processing (IDAP) pp. 1 - 4
Main Authors ELDEM, Ayse, ELDEM, Huseyin, USTUN, Deniz
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2018
Subjects
Classification
Classification algorithms
Computational modeling
Deep learning
Deep Neural Network
Iris
Iris recognition
Machine learning algorithms
Neural networks
Online AccessGet full text
DOI10.1109/IDAP.2018.8620866

Cover

More Information
Summary:In recent years, deep neural network (DNN) has been frequently used for classification. In this study, iris flowers having 3 different types are classified by using DNN which are utilized the width and length of petal and sepal features as input. Some experiments are made for the iris dataset by using different activation functions and different epoch numbers. Then, the activation function which gives the best result is determined. The classification success of the developed model is achieved 96% for the iris dataset.
DOI:10.1109/IDAP.2018.8620866