| Creator |
|
|
|
|
|
| Language |
|
| Publisher |
|
|
|
| Date |
|
| Source Title |
|
| Vol |
|
| Issue |
|
| First Page |
|
| Last Page |
|
| Publication Type |
|
| Access Rights |
|
| JaLC DOI |
|
| Related DOI |
|
| Related URI |
|
| Relation |
|
| Abstract |
Based on radial basis function neural network (RBFN) and perceptron neural network, this paper built a new four-layer feed-forward neural network named radial basis perceptron network (RBPN). This net...work can be summarized as follows: (1) It is selective connection between the units of two hidden layers; (2) The number of units of hidden layers is to be defined dynamically; (3) During learning procedure, RBPN adopts input-output clustering (IOC) method, and the appearance parameters of centers is self-adjustable. This is illustrated using an example taken from applications for component analysis of civil building materials. Simulation shows that RBPN can be used to predict the components of civil building materials successfully and gets good generalization ability.show more
|
Export Mendeley
p067