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...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Shakeel Shafiq, Tayyaba Azim
Formato:	Artigo
Idioma:	Inglês
Publicado em:	PeerJ Inc. 2021-05-01
coleção:	PeerJ Computer Science
Assuntos:	Local binary pattern (LBP) Support vector machines (SVM) k-nearest neighbour (k-NN) Convolutional neural network (CNN) Discriminatively boosted alternative to pooling (DBAP) layer Improved LeNet
Acesso em linha:	https://peerj.com/articles/cs-497.pdf
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!