Deakin University
Browse

File(s) under permanent embargo

An online transfer learning RBF neural network for cross domain data classification

Version 2 2024-06-03, 06:45
Version 1 2015-03-11, 15:10
chapter
posted on 2024-06-03, 06:45 authored by SC Tan, Chee Peng LimChee Peng Lim, M Seera
In this paper, a Radial Basis Function Network (RBFN) trained with the Dynamic Decay Adjustment (DDA) algorithm (i.e., RBFNDDA) is deployed as an incremental learning model for tackling transfer learning problems. An online learning strategy is exploited to allow the RBFNDDA model to transfer knowledge from one domain and applied to classification tasks in a different yet related domain. An experimental study is carried out to evaluate the effectiveness of the online RBFNDDA model using a benchmark data set obtained from a public domain. The results are analyzed and compared with those from other methods. The outcomes positively reveal the potentials of the online RBFNDDA model in handling transfer learning tasks.

History

Volume

262

Chapter number

22

Pagination

210-218

ISSN

0922-6389

ISBN-13

9781614994046

Language

eng

Publication classification

B Book chapter, B1 Book chapter

Copyright notice

2014, IOS Press

Extent

79

Editor/Contributor(s)

Neves-Silva R, Tshirintzis GA, Uskov V, Howlett RJ, Jain LC

Publisher

IOS Press

Place of publication

Amsterdam, The Netherlands

Title of book

Volume 262: Smart Digital Futures 2014