Figure 1. Three layers of CNN algorithm. - https://doi.org/10.70594/brain/17.1/2

Read full text Summarise with VIRAT
Authors: Pratiksha Deshmukh, Harshali Patil
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In previous studies on image processing, authors usually use CNNs to analyse images because they are a type of deep, feed-forward artificial neural network (Cabada et al., 2019). Other image recognition methods require more complex image preparation than a CNN. This is because a CNN's convolutional component extracts an image's key properties. Three different kinds of layers make up the CNNs' multilayered architecture. The primary characteristics and patterns in an image are extracted by the first layer, known as the convolutional layer. The pooling layer reduces the number of features taken from the previous layer. The features and patterns gathered from the earlier layers are then categorised by a fully connected layer. A CNN's three layers are shown in Figure 1.

Fields of Study & Subjects

Advanced Neural Network Applications Computer Science and Engineering Neural Networks and Applications

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
27 March 2026
Language
EN