Knowledge acquisition and revision via neural networks

College

College of Computer Studies

Department/Unit

Software Technology

Document Type

Conference Proceeding

Source Title

IEEE International Conference on Neural Networks - Conference Proceedings

Volume

2

First Page

1365

Last Page

1370

Publication Date

12-1-2004

Abstract

We investigate how knowledge acquired by a neural network from one input environment can be transferred and revised for similar application in a new environment. Knowledge revision is achieved by re-training the neural network. Knowledge common to both environments are retained, while localized knowledge components are introduced during network retraining. Various network performance measures are computed to measure how much knowledge is transferred and revised. Furthermore, because the knowledge acquired by a neural network can be expressed as an accurate set of simple rules, we are able to compare knowledge extracted from one network with that from another. In a cross-national study of car image perceptions, a comparison of the original and revised knowledge gives us insights into the commonalities and differences in brand perceptions across countries.

html

Digitial Object Identifier (DOI)

10.1109/IJCNN.2004.1380147

Disciplines

Computer Sciences | Software Engineering

Keywords

Neural networks (Computer science); Self-organizing systems

Upload File

wf_no

This document is currently not available here.

Share

COinS