Two-step Approach in the Training of Regulated Activation Weight Neural Networks (RAWN)
详细信息 查看全文
- 作者：Te Braake ; H. A. B. ; Van Can ; H. J. L. ; Van Straten ; G. ; Verbruggen ; H. B.
- 关键词：Training ; feedforward neural networks ; nonlinear optimization ; Levenberg-Marquardt training ; backpropagation
- 刊名：Engineering Applications of Artificial Intelligence
- 出版年：1997
- 出版时间：April, 1997
- 年：1997
- 卷：10
- 期：2
- 页码：157-170
- 全文大小：1.17 M
文摘
Feedforward neural networks with a single hidden layer of neurons and a linear output layer are a convenient way to model a nonlinear input-output mapping. If the activation weights, i.e. the weights between input and hidden-layer neurons, are known, an estimation problem remains that is linear in the parameters. This can easily be solved by standard least-squares methods. The problem thus reduces to finding appropriate activation weights. This paper describes a method to obtain the activation weights, based on local linear approximations, which also can be solved with standard least-squares techniques. The local linear models can be obtained by fuzzy clustering methods. The method is demonstrated on a simple example. With the proposed method the weights are obtained very fast, and the results are good. The method is also flexible with respect to the incorporation of a priori process knowledge.