A novel method (based on the characteristics of scatter matrices and frequency-sensitive competitive learning) for training the hidden layer of a radial basis function neural network is proposed. The method is demonstrated to be robust and to outperform the state-of-the-art algorithm.
|Original language||English (US)|
|Number of pages||2|
|State||Published - Apr 2 1998|
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering