Projection-based gradient descent training of radial basis function networks

被引：0

作者：

Muezzinoglu, MK ^{[1
]}

Zurada, JM ^{[1
]}

机构：

[1] Univ Louisville, Computat Intelligence Lab, Louisville, KY 40292 USA

来源：

2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS | 2004年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new Radial Basis Function (RBF) network training procedure that employs a linear projection technique along parameter search is proposed. To be applied simultaneously with the conventional center and/or weight adjustment methods, a gradient descent iteration on the width parameters of RBF units is introduced. The projection mechanism used by the procedure avoids negative width parameters and enables detection of redundant units, which can then be pruned from the network. Proposed training approach is applied to design a feedback neuro-controller for a nonlinear plant to track a desired trajectory.

引用

下载

页码：1297 / 1302

页数：6

共 50 条

[1] Training radial basis functions by gradient descent
Fernández-Redondo, M
Hernández-Espinosa, C
Ortiz-Gómez, M
Torres-Sospedra, J
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING - ICAISC 2004, 2004, 3070 : 184 - 189
[2] Gradient descent training of Radial Basis Functions
Fernández-Redondo, M
Hernández-Espinosa, C
Ortiz-Gómez, M
Torres-Sospedra, J
ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1, 2004, 3173 : 229 - 234
[3] Training Radial Basis Functions by gradient descent
Fernandez-Redondo, Mercedes
Toffes-Sospedra, Joaquin
Hernandez-Espinosa, Carlos
2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, 2006, : 756 - +
[4] Tutorial on the generation of ergodic trajectories with projection-based gradient descent
Dressel, Louis
Kochenderfer, Mykel J.
IET CYBER-PHYSICAL SYSTEMS: THEORY & APPLICATIONS, 2019, 4 (02) : 89 - 100
[5] Some experiments on training Radial Basis Functions by gradient descent
Fernández-Redondo, M
Hernández-Espinosa, C
Ortiz-Gómez, M
Torres-Sospedra, J
NEURAL INFORMATION PROCESSING, 2004, 3316 : 428 - 433
[6] A hybrid projection-based and radial basis function architecture: Initial values and global optimisation
Cohen, S
Intrator, N
PATTERN ANALYSIS AND APPLICATIONS, 2002, 5 (02) : 113 - 120
[7] An experimental study on training radial basis functions by gradient descent
Torres-Sospedra, Joaquin
Hernandez-Espinosa, Carlos
Fernandez-Redondo, Mercedes
ARTIFICIAL NEURAL NETWORKS IN PATTERN RECOGNITION, PROCEEDINGS, 2006, 4087 : 81 - 92
[8] A Hybrid Projection-based and Radial Basis Function Architecture: Initial Values and Global Optimisation
S. Cohen
N. Intrator
Pattern Analysis & Applications, 2002, 5 : 113 - 120
[9] Sequential Projection-Based Metacognitive Learning in a Radial Basis Function Network for Classification Problems
Babu, Giduthuri Sateesh
Suresh, Sundaram
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2013, 24 (02) : 194 - 206
[10] Gradient descent learning of radial-basis neural networks
Karayiannis, NB
1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 1815 - 1820

← 1 2 3 4 5 →