Application of function link net to recognition of radar targets
De-Shuang Huang, Mao Er-ke, Han Yueqiu · 2002
This paper studies the mechanism for classification of feedforward neural networks from the geometric viewpoints. It is pointed out that the multilayer perceptron networks (MLPNs) realize hyperplane divisions in the pattern space, and the FLN realize hypercurved divisions. We give a form of generalized function link nets (GFLN), and discuss the application of a special GFLN to recognition of radar targets, and give several experimental results.