FAST LEARNING WITH INCREMENTAL RBF NETWORKS

被引：126

作者：

FRITZKE, B ^{[1
]}

机构：

[1] RUHR UNIV BOCHUM, INST NEUROINFORMAT, D-44780 BOCHUM, GERMANY

来源：

NEURAL PROCESSING LETTERS | 1994年 / 1卷 / 01期

关键词：

D O I：

10.1007/BF02312392

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a new algorithm for the construction of radial basis function (RBF) networks. The method uses accumulated error information to determine where to insert new units. The diameter of the localized units is chosen based on the mutual distances of the units. To have the distance information always available, it is held up-to-date by a Hebbian learning rule adapted from the ''Neural Gas'' algorithm. The new method has several advantages over existing methods and is able to generate small, well-generalizing networks with comparably few sweeps through the training data.

引用

页码：2 / 5

页数：4

共 50 条

[1] Adaptive learning in incremental learning RBF networks
Nagabhushan, TN
Padma, SK
[J]. NEURAL INFORMATION PROCESSING, 2004, 3316 : 471 - 476
[2] A fast incremental learning algorithm of RBF networks with long-term memory
Okamoto, K
Ozawa, S
Abe, S
[J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 102 - 107
[3] Incremental learning and forgetting in RBF networks and SVMs with applications to financial problems
Nakayama, H
Hattori, A
[J]. KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 1, PROCEEDINGS, 2003, 2773 : 1109 - 1115
[4] On the generalization of incremental learning RBF neural networks trained with significant patterns
Nagabhushan, T. N.
Padma, S. K.
[J]. 2007 6TH INTERNATIONAL CONFERENCE ON INFORMATION, COMMUNICATIONS & SIGNAL PROCESSING, VOLS 1-4, 2007, : 859 - 863
[5] Incremental structure learning of three-layered Gaussian RBF networks
Coufal, D
[J]. COMPUTATIONAL SCIENCE-ICCS 2002, PT III, PROCEEDINGS, 2002, 2331 : 584 - 593
[6] The Locality of RBF-SVM for Incremental Learning
Emara, Wael
Kantardzic, Mehmed
[J]. 2009 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DATA MINING, 2009, : 355 - 362
[7] Fast Adaptive Gradient RBF Networks For Online Learning of Nonstationary Time Series
Liu, Tong
Chen, Sheng
Liang, Shan
Gan, Shaojun
Harris, Chirs J.
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2020, 68 : 2015 - 2030
[8] Fast and efficient training of RBF networks
Buchtala, O
Hofmann, A
Sick, B
[J]. ARTIFICIAL NEURAL NETWORKS AND NEURAL INFORMATION PROCESSING - ICAN/ICONIP 2003, 2003, 2714 : 43 - 51
[9] Hybrid learning of RBF networks
Neruda, R
Kudová, P
[J]. COMPUTATIONAL SCIENCE-ICCS 2002, PT III, PROCEEDINGS, 2002, 2331 : 594 - 603
[10] Hybrid learning of RBF networks
Neruda, Roman
Kudová, Petra
[J]. Neural Network World, 2002, 12 (06) : 573 - 585

← 1 2 3 4 5 →