Kernel-blending connection approximated by a neural network for image classification

Kernel-blending connection approximated by a neural network for image classification

Abstract This paper proposes a kernel-blending connection approximated by a neural network (KBNN) for image classification. A kernel mapping connection structure, guaranteed by the function approximation theorem, is devised to blend feature extraction and feature classification through neural networ...

Full description

Bibliographic Details
Main Authors: Xinxin Liu, Yunfeng Zhang, Fangxun Bao, Kai Shao, Ziyi Sun, Caiming Zhang
Format: Article
Language:English
Published: SpringerOpen 2020-09-01
Series:Computational Visual Media
Subjects:
image classification
blending neural network
function approximation
kernel mapping connection
generalizability
Online Access:https://doi.org/10.1007/s41095-020-0181-9

Internet

https://doi.org/10.1007/s41095-020-0181-9

Similar Items