BriefGPT.xyz
Dec, 2015
用于图像分类的核主成分分析网络
Kernel principal component analysis network for image classification
HTML
PDF
Dan Wu, Jiasong Wu, Rui Zeng, Longyu Jiang, Lotfi Senhadji...
TL;DR
介绍一种名为 KPCANet 的深度学习网络，可以通过核主成分分析将非线性特征分类为线性，提高分类准确性，在人脸识别、物体识别和手写数字识别等任务中表现良好，优于主成分分析网络 PCANet，同时具有光照不变性和抗干扰性。
Abstract
In order to classify the nonlinear feature with linear classifier and improve the classification accuracy, a
deep learning
network named
kernel principal component analysis
network (
→