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
Recommended Citation
Azcarraga, A. P., Hsieh, M. H., Pan, S., & Setiono, R. (2004). Knowledge acquisition and revision via neural networks. IEEE International Conference on Neural Networks - Conference Proceedings, 2, 1365-1370. https://doi.org/10.1109/IJCNN.2004.1380147
Disciplines
Computer Sciences | Software Engineering
Keywords
Neural networks (Computer science); Self-organizing systems
Upload File
wf_no