Empirical Evaluation of CNN's Activation Functions and Pooling Layers for Diabetic Retinopathy Classification

Volume 15 No 3 (2017)

Ranjith Kumar Siddoju, Dr. Manjunarha Reddy

DOI: 10.48047/nq.2017.15.3.1061

Abstract

These days, convolution neural networks are at the pinnacle of their growth. This paper's goal is to examine how a classification model behaves in order to automatically identify diabetic eye damage. Four distinct pooling layer types with four different activation functions are used to test a Convolution Neural Network model with four convolution layers and two fully connected layers. The model's output is assessed using several evaluation parameters while utilizing the same layer of various types. Different outcomes have been noted based on different pooling layer and activation function combinations.

Keywords

Fundus Pictures, Activation Function, Pooling, CNN, And Diabetic Retinopathy

Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.