SHIFT INVARIANCE AND THE NEOCOGNITRON

被引：25

作者：

BARNARD, E ^{[1
]}

CASASENT, D ^{[1
]}

机构：

[1] CARNEGIE MELLON UNIV,DEPT ELECT & COMP ENGN,CTR EXCELLENCE OPT DATA PROC,PITTSBURGH,PA 15213

来源：

NEURAL NETWORKS | 1990年 / 3卷 / 04期

关键词：

Neocognitron; Neural classifiers; Pattern recognition; Shift invariance;

D O I：

10.1016/0893-6080(90)90023-E

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We investigate the ability of the neocognitron to perform shift-invariant pattern recognition. Both an intuitive analysis and a more formal investigation show that the performance of the neocognitron is not intrinsically shift invariant, and that certain model parameters must be chosen appropriately to obtain approximate shift invariance. It is shown how these parameters should be chosen to reach a compromise between invariance and classification sensitivity. © 1990.

引用

页码：403 / 410

页数：8

共 10 条

[1]

Ballard DH, 1982, COMPUTER VISION

[2] POSITION, ROTATION, AND SCALE INVARIANT OPTICAL CORRELATION [J].