INVARIANCE AND NEURAL NETS

被引：40

作者：

BARNARD, E ^{[1
]}

CASASENT, D ^{[1
]}

机构：

[1] CARNEGIE MELLON UNIV,DEPT QUIM ANALIT,PITTSBURGH,PA 15213

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1991年 / 2卷 / 05期

关键词：

D O I：

10.1109/72.134287

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Invariance with respect to certain transformations is one of the main tasks of pattern-recognition systems. We study various techniques for obtaining this invariance with neural net classifiers and identify the invariant-feature technique as the most suitable for current neural classifiers. A new formulation of invariance in terms of constraints on the feature values leads to a general method for transforming any given feature space so that it becomes invariant to specified transformations. A case study using range imagery is used to exemplify these ideas, and good performance is obtained.

引用

页码：498 / 508

页数：11

共 31 条

[1] IMAGE NORMALIZATION BY COMPLEX MOMENTS
ABUMOSTAFA, YS
PSALTIS, D
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1985, 7 (01) : 46 - 55
[2] Amari S., 1968, RAAG MEMOIRS, V4, P553
[3] [Anonymous], 1987, LEARNING INTERNAL RE
[4] Ballard DH, 1982, COMPUTER VISION
[5] BARNARD E, 1990, APPL OPTICS, V29, P2603
[6] BARNARD E, 1989, IEEE T SYST MAN CYBE, V19
[7] A NEURAL NETWORK FOR INVARIANT PATTERN-RECOGNITION
BIENENSTOCK, E
VONDERMALSBURG, C
[J]. EUROPHYSICS LETTERS, 1987, 4 (01): : 121 - 126
[8] EXPERIMENTS ON NEURAL NET RECOGNITION OF SPOKEN AND WRITTEN TEXT
BURR, DJ
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (07): : 1162 - 1168
[9] COMPUTER GENERATED HOLOGRAMS IN PATTERN-RECOGNITION - A REVIEW
CASASENT, D
[J]. OPTICAL ENGINEERING, 1985, 24 (05) : 724 - 730
[10] UNIFIED SYNTHETIC DISCRIMINANT FUNCTION COMPUTATIONAL FORMULATION
CASASENT, D
[J]. APPLIED OPTICS, 1984, 23 (10): : 1620 - 1627

← 1 2 3 4 →