抄録
This paper presents a constructive neural network with sigmoidal units and multiplication units, which can uniformly approximate any continuous function on a compact set in multi-dimensional input space. This network provides a more efficient and regular architecture compared to existing higher-order feedforward networks while maintaining their fast learning property. Proposed network provides a natural mechanism for incremental network growth. Simulation results on function approximation problem are given to highlight the capability of the proposed network. In particular, self-organizing process with RasID learning algorithm developed for the network is shown to yield smooth generation and steady learning.
本文言語 | English |
---|---|
ページ(範囲) | 135-140 |
ページ数 | 6 |
ジャーナル | Research Reports on Information Science and Electrical Engineering of Kyushu University |
巻 | 8 |
号 | 2 |
出版ステータス | Published - 2003 9月 1 |
ASJC Scopus subject areas
- コンピュータ サイエンス(全般)
- 電子工学および電気工学