Covering framework and primary direction neural network
覆盖框架与主方向神经网络

Some widely used artificial neural networks such as BP, RBF and ARTMAP were discussed on the common points they shared when solving nonlinear regression problems. A framework, proposed accordingly, suggested that such problems should be implemented in two steps: sample covering and model-based map regression. This idea stems from two aspects, i.e. simulation of human brain's information processing and Biometric Pattern Recognition (BPR). As an instance, a new network named as Primary Direction Neural Networ...