Abstract

A Convolutional Neural Network (CNN) is a type of Deep Learning architecture that has gained in popularity for classification problems. The performance of a CNN is not only tied closely with the data that it is trained with, but also the CNN's own architecture. It is the purpose of this study to analyze how architecture changes to the feature extraction portion of a CNN affects its performance for a given image classification problem. This study resulted in concluding that the number of layers is not an indicator of a CNN's performance; the number of trainable parameters in a CNN are not an indicator of performance; singleton convolutional layer groups can have similar or better performance than groups consisting of multiple convolutional layers; and proving that utilizing input data that minimizes noise while maximizing features of interest to train and test a CNN results in improved model performance.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.