학술논문
A knowledge-based approach to supervised incremental learning
Document Type
Conference
Author
Source
Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94) Neural networks Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on. 3:1793-1798 vol.3 1994
Subject
Language
Abstract
How to learn new knowledge without forgetting old knowledge is a key issue in designing an incremental-learning neural network. In this paper, we present a rule-based connectionist approach in which old knowledge is preserved by bounding weight modifications. In addition, some heuristics are developed for avoiding overtraining of the network and adding new hidden units. The feasibility of this approach is demonstrated for classification problems including the iris and the promoter domains.ETX