Modified high-order neural network for invariant pattern recognition

被引：32
|
作者：
Artyomov, E [1 ]
Yadid-Pecht, O [1 ]
机构：
[1] Ben Gurion Univ Negev, VLSI Syst Ctr, IL-84105 Beer Sheva, Israel
来源：
PATTERN RECOGNITION LETTERS | 2005年 / 26卷 / 06期
关键词：
HONN; high-order neural networks; invariant pattern recognition; binary patterns;
D O I：
10.1016/j.patrec.2004.09.029
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A modification for high-order neural networks (HONN) is described. The proposed modified HONN takes into account prior knowledge of the binary patterns that must be learned. This significantly reduces hence computation time as well as memory requirements for network configuration and weight storage. An "approximately equal triangles" scheme for weight sharing is also proposed. These modifications enable the efficient computation of HONNs for image fields of greater that 100 x 100 pixels without any loss of pattern information. (c) 2004 Elsevier B.V. All rights reserved.
引用
收藏
页码：843 / 851
页数：9
相关论文
共 50 条
  • [1] Speaker recognition method with high-order neural network based on biomimetics pattern recognition
    Wu, Yan
    Jin, Mingxi
    Wang, Shoujue
    Jisuanji Gongcheng/Computer Engineering, 2006, 32 (12): : 184 - 186
  • [2] An adaptive high-order neural tree for pattern recognition
    Foresti, GL
    Dolso, T
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2004, 34 (02): : 988 - 996
  • [3] TRANSLATION, ROTATION, AND SCALE INVARIANT PATTERN-RECOGNITION BY HIGH-ORDER NEURAL NETWORKS AND MOMENT CLASSIFIERS
    PERANTONIS, SJ
    LISBOA, PJG
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (02): : 241 - 251
  • [4] On a higher-order neural network for distortion invariant pattern recognition
    Kaita, T
    Tomita, S
    Yamanaka, J
    PATTERN RECOGNITION LETTERS, 2002, 23 (08) : 977 - 984
  • [5] Fast learning high-order neural networks for pattern recognition
    Zhang, SJ
    Jing, ZL
    Li, JX
    ELECTRONICS LETTERS, 2004, 40 (19) : 1207 - 1208
  • [6] A HIGHER-ORDER NEURAL NETWORK FOR DISTORTION INVARIANT PATTERN-RECOGNITION
    KANAOKA, T
    CHELLAPPA, R
    YOSHITAKA, M
    TOMITA, S
    PATTERN RECOGNITION LETTERS, 1992, 13 (12) : 837 - 841
  • [7] A NEURAL NETWORK FOR INVARIANT PATTERN-RECOGNITION
    BIENENSTOCK, E
    VONDERMALSBURG, C
    EUROPHYSICS LETTERS, 1987, 4 (01): : 121 - 126
  • [8] Illuminant-Invariant Face Recognition Using High-Order Local Derivative Pattern
    Kwon, Oh-Seol
    JOURNAL OF IMAGING SCIENCE AND TECHNOLOGY, 2018, 62 (01)
  • [9] High-Order Associative Memories for Pattern Recognition
    Ciocoiu, Iulian B.
    NEW ASPECTS OF SYSTEMS, PTS I AND II, 2008, : 509 - +
  • [10] Face Recognition with Multi-channel Local Mesh High-order Pattern Descriptor and Convolutional Neural Network
    Asif, M. Daud Abdullah
    Gao, Yongsheng
    Zhou, Jun
    2018 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA), 2018, : 500 - 506
12345