PCANet: An energy perspective - Université de Rennes Accéder directement au contenu
Article Dans Une Revue Neurocomputing Année : 2018

PCANet: An energy perspective

Résumé

The principal component analysis network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various databases. However, the visualization or explanation of the PCANet is lacked. In this paper, we try to explain why PCANet works well from energy perspective point of view based on a set of experiments. The paper shows that the error rate of PCANet is qualitatively correlated with the inverse of the logarithm of BlockEnergy, which is the energy after the block sliding process of PCANet, and also this relation is quantified by using curve fitting method. The proposed energy explanation approach can also be used as a testing method for checking if every step of the constructed networks is necessary.
Fichier principal
Vignette du fichier
Wu et al_2018_PCANet.pdf (1.29 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01839334 , version 1 (10-09-2018)

Identifiants

Citer

Jiasong Wu, Shijie Qiu, Youyong Kong, Longyu Jiang, Yang Chen, et al.. PCANet: An energy perspective. Neurocomputing, 2018, 313, pp.271-287. ⟨10.1016/j.neucom.2018.06.025⟩. ⟨hal-01839334⟩
141 Consultations
150 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More