(四)multi-layer perceptron network
Can solve Exclusive Linear-non-classifiable input patterns,这解决了单层感知器的缺点.本质上是由于加了隐藏层的原因。
Each layer equivalent to a Single-Layer Perceptron Networks
qth layer forms a nq-1 dimension Super-Plane perceptron networks, which can linearly classify the
input patterns of this layer .Through Multi-Layer combination, eventually can implement the complex classification to input patterns.
下面是一个具体解决线性不可分思路。