The hidden layer design of the MVQ neural network

被引：0

作者：

Abouali, AH ^{[1
]}

Porter, WA ^{[1
]}

机构：

[1] Egyptian Res Ctr, Cairo 11435, Egypt

来源：

THIRTIETH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY (SSST) | 1998年

关键词：

D O I：

10.1109/SSST.1998.660103

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this study, we introduce the first part of neural network classifiers design methodology. The design has a lot of the desired features. The design is based on a preprocessing stage of multiple class vector quantization, MVQ, algorithm. The algorithm extracts the information from the training set. The outcome of this stage fully defines the first hidden layer of the network. The methodology not only has better performance but also provides insights to why and how the neural network works.

引用

下载

页码：393 / 396

页数：4

共 50 条

[1] On neural network design - Part I: Using the MVQ algorithm
Porter, WA
Abou-ali, AH
CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 1998, 17 (02) : 195 - 218
[2] On neural network design — Part I: Using the MVQ algorithm
W. A. Porter
A. H. Abou-ali
Circuits, Systems and Signal Processing, 1998, 17 : 195 - 218
[3] Observer design for the single hidden layer fuzzy recurrent wavelet neural network
Wen, Xin
Li, Xin
Wang, Ershen
Dianbo Kexue Xuebao/Chinese Journal of Radio Science, 2015, 30 (06): : 1197 - 1204
[4] Optimizing One-hidden Layer Neural Network Design Using Evolutionary Programming
Sulaiman, S. I.
Rahman, T. K. Abdul
Musirin, I.
CSPA: 2009 5TH INTERNATIONAL COLLOQUIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, PROCEEDINGS, 2009, : 288 - 293
[5] NEURAL NETWORK PRUNING BY FUSING HIDDEN LAYER UNITS
KAMEYAMA, K
KOSUGI, Y
IEICE TRANSACTIONS ON COMMUNICATIONS ELECTRONICS INFORMATION AND SYSTEMS, 1991, 74 (12): : 4198 - 4204
[6] Neural network without bias neuron for hidden layer
Majetic, D.
Brezak, D.
Novakovic, B.
Kasac, J.
Annals of DAAAM for 2005 & Proceedings of the 16th International DAAAM Symposium: INTELLIGENT MANUFACTURING & AUTOMATION: FOCUS ON YOUNG RESEARCHES AND SCIENTISTS, 2005, : 239 - 240
[7] Spectral technique for hidden layer neural network training
Windeatt, T
Tebbs, R
PATTERN RECOGNITION LETTERS, 1997, 18 (08) : 723 - 731
[8] The Design of Image Compression with BP Neural Network Based on the Dynamic Adjusting Hidden Layer Nodes
Li Jing
Wu Xinhui
Qin Changhai
Zhao Jing
MATERIALS SCIENCE AND INFORMATION TECHNOLOGY, PTS 1-8, 2012, 433-440 : 3797 - +
[9] INTERPRETING THE HIDDEN LAYER IN A NEURAL NETWORK FOR A SPEECH RECOGNITION TASK
KAMM, C
STREETER, LA
KANEESRIG, Y
NEURAL NETWORKS FROM MODELS TO APPLICATIONS, 1989, : 523 - 530
[10] Emergence of clusters in the hidden layer of a dynamic recurrent neural network
Draye, JP
Cheron, G
Libert, G
Godaux, E
BIOLOGICAL CYBERNETICS, 1997, 76 (05) : 365 - 374

← 1 2 3 4 5 →