3-LAYER NEURAL NETWORK MODELS FOR ROTATED PATTERNS RECOGNITION

被引：0

作者：

SUZAKI, K ^{[1
]}

ARAYA, S ^{[1
]}

NAKAMURA, R ^{[1
]}

机构：

[1] KUMAMOTO UNIV, FAC ENGN, DEPT ELECT ENGN & COMP SCI, KUMAMOTO 860, JAPAN

来源：

IFIP TRANSACTIONS A-COMPUTER SCIENCE AND TECHNOLOGY | 1992年 / 12卷

关键词：

MODELS; DESIGN METHODOLOGY; APPLICATIONS;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper proposes two types of neural net models for learning and recognizing rotated patterns. They are :(1) a rotation invariant learning model; (2) a copy-learning model. These are all 3-layer neural nets. Their learning is based on the error back-propagation algorithm. The first one has the same recognition ability as Widrow's model while featuring simple learning and recognition mechanisms, making it easy to build a net. The second one employs the efficient use of copying, making it possible to recognize rotation angles, which cannot be recognized with conventional models. Each of the two models features a simple net structure of compact size, and a substantially reduced time, required for learning and recognition. The effectiveness of the proposed models has been verified through experiments.

引用

页码：667 / 673

页数：7

共 50 条

[1] EXPERIMENTAL DEMONSTRATION OF OPTICAL 3-LAYER NEURAL NETWORK
KASAMA, N
HAYASAKI, Y
YATAGAI, T
MORI, M
ISHIHARA, S
JAPANESE JOURNAL OF APPLIED PHYSICS PART 2-LETTERS & EXPRESS LETTERS, 1990, 29 (08): : L1565 - L1568
[2] Using a 3-Layer Artificial Neural Network to Predict S-Nitrosylation
Anand, Vijay
Liu, Ziping
Gow, Andrew
FASEB JOURNAL, 2021, 35
[3] 2-LAYER AND 3-LAYER MODELS OF URANUS
HOREDT, GP
HUBBARD, WB
MOON AND THE PLANETS, 1983, 29 (03): : 229 - 236
[4] Image Classification with a 3-Layer SOA-Based Photonic Integrated Neural Network
Shi, B.
Calabretta, N.
Stabile, R.
2019 24TH OPTOELECTRONICS AND COMMUNICATIONS CONFERENCE (OECC) AND 2019 INTERNATIONAL CONFERENCE ON PHOTONICS IN SWITCHING AND COMPUTING (PSC), 2019,
[5] Structured Output Layer Neural Network Language Models for Speech Recognition
Le, Hai-Son
Oparin, Ilya
Allauzen, Alexandre
Gauvain, Jean-Luc
Yvon, Francois
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2013, 21 (01): : 195 - 204
[6] Efficient VLSI implementation of a 3-layer threshold network
Kim, JH
Park, SK
Han, YN
Oh, H
Han, MS
1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 888 - 893
[7] A study on generalization ability of 3-layer recurrent neural networks
Ninomiya, H
Sasaki, A
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1063 - 1068
[8] THE PARALLEL COMPLEXITY OF FINDING A BLOCKING FLOW IN A 3-LAYER NETWORK
CHERIYAN, J
MAHESHWARI, SN
INFORMATION PROCESSING LETTERS, 1989, 31 (03) : 157 - 161
[9] Recognition of rotated patterns using neocognitron
Satoh, S
Kuroiwa, J
Aso, H
Miyake, S
PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 112 - 116
[10] NEURAL NETWORK MODELS FOR PROMOTER RECOGNITION
LUKASHIN, AV
ANSHELEVICH, VV
AMIRIKYAN, BR
GRAGEROV, AI
FRANKKAMENETSKII, MD
JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS, 1989, 6 (06): : 1123 - 1133

← 1 2 3 4 5 →