Open AccessImpact of Hidden Dense Layers in Convolutional Neural Network to enhance Performance of Classification Model
Author(s) -
V L Helen Josephine,
A. Nirmala,
Vijaya Lakshmi Alluri
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1131/1/012007
Subject(s) - convolutional neural network , computer science , deep learning , artificial intelligence , convolution (computer science) , artificial neural network , machine learning , layer (electronics) , pattern recognition (psychology) , materials science , composite material
Education and Health care sectors are two predominant areas where societal growth is expected through innovation and technology development. Machine Learning and Deep learning classification models have been entertained in predicting, detecting, and diagnosing major diseases in the early stage. In this research paper, we have analyzed the impact of hidden dense layers in the Convolution neural network to improve the performance of the classification model. Three different classification deep network models have been constructed, analyzed and the result was tested with a diabetes dataset. Results concluded that the more layers with deeper the network better was the classification performance. The classification model with six hidden dense layers outperforms all other less number of hidden dense layers.