Introduction - If you have any usage issues, please Google them yourself
RBF network can approximate arbitrary non-linear functions, can deal with the laws that are difficult to analyse in the system, has good generalization ability, and has very fast learning.
The convergence rate has been successfully applied to non-linear function approximation, time series analysis, data classification, pattern recognition, information processing, image processing and system construction.
Modeling, control and fault diagnosis.
Simply explain why RBF network learning converges faster. When one or more adjustable parameters (weights or thresholds) of the network are applied to any output
When there is an impact, such a network is called a global approximation network. For each input, each weight on the network has to be adjusted, which leads to global approximation.
The learning speed of the network is very slow. BP network is a typical example.
If only a few connection weights affect the output for a local area of the input space,