核主成分分析
主成分分析
特征向量
非线性系统
核(代数)
数学
模式识别(心理学)
像素
多项式的
核方法
人工智能
操作员(生物学)
多项式核
特征提取
组分(热力学)
算法
作者
Bernhard Schölkopf,Alexander J. Smola,Klaus-Robert Müller
标识
DOI:10.1162/089976698300017467
摘要
A new method for performing a nonlinear form of principal component analysis is proposed. By the use of integral operator kernel functions, one can efficiently compute principal components in high-dimensional feature spaces, related to input space by some nonlinear map—for instance, the space of all possible five-pixel products in 16 × 16 images. We give the derivation of the method and present experimental results on polynomial feature extraction for pattern recognition.
科研通智能强力驱动
Strongly Powered by AbleSci AI