抄録
Nonlinear radial basis functions at the single layer hidden units are effective in generating complex nonlinear mapping and at the same time facilitate fast linear learning. In this work, we propose a model and an algorithm to arrive at a near optimum initial configuration very quickly. Thus the position of the hidden units in the input space and the connection weights from the hidden units to the output units, instead of arbitrarily, are optimally set. Simulations on this initial configuration are performed. Different parameters are further trained and their effects experimented.
本文言語 | English |
---|---|
ホスト出版物のタイトル | 1993 IEEE International Conference on Neural Networks |
編集者 | Anon |
Place of Publication | Piscataway, NJ, United States |
出版社 | Publ by IEEE |
ページ | 466-472 |
ページ数 | 7 |
ISBN(印刷版) | 0780312007 |
出版ステータス | Published - 1993 |
イベント | 1993 IEEE International Conference on Neural Networks - San Francisco, CA, USA 継続期間: 1993 3月 28 → 1993 4月 1 |
Other
Other | 1993 IEEE International Conference on Neural Networks |
---|---|
City | San Francisco, CA, USA |
Period | 93/3/28 → 93/4/1 |
ASJC Scopus subject areas
- 工学(全般)