期刊
NEUROCOMPUTING
卷 313, 期 -, 页码 271-287出版社
ELSEVIER
DOI: 10.1016/j.neucom.2018.06.025
关键词
Deep learning; Convolutional neural networks; PCANet; Error rate; Energy; Image recognition
资金
- National Key R&D Program of China [2017YFC0107900]
- National Natural Science Foundation of China [61271312, 61201344, 61773117, 61401085, 31571001, 31640028, 31400842, 61572258, 11301074]
- Natural Science Foundation of Jiangsu Province [BK20150650]
- '333' project [BRA2015288]
- Short-term Recruitment Program of Foreign Experts [WQ20163200398]
- Qing Lan Project
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. (C) 2018 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据