Introspective analysis of convolutional neural networks for improving discrimination performance and feature visualisation

Deep neural networks have been widely explored and utilised as a useful tool for feature extraction in computer vision and machine learning. It is often observed that the last fully connected (FC) layers of convolutional neural network possess higher discrimination power as compared to the convoluti...

Full description

Bibliographic Details
Main Authors: Shakeel Shafiq, Tayyaba Azim
Format: Article
Language:English
Published: PeerJ Inc. 2021-05-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-497.pdf