Artificial neural Network (Artificial neural netwroks) Notes-basic BP algorithm

Single-layer perceptron does not solve the XOR problem

Artificial Neural Networks (Artificial neural netwroks) have also fallen into low ebb due to this problem, but the multilayer Perceptron presented later has made the artificial neural network (Artificial neural netwroks) again high.

The BP network is the most extensive one. The specific principle introduction can be obtained through the network here only describes the algorithm flow

The basic BP algorithm

1 for k=1 ToL do

Initialize w^ (k)

2 initialization Precision control parameter ε

3 e=ε+1

4 while E>εdo

4.1 E=0
4.2 对S中的每个样本(Xp,Yp):
4.2.1计算出Xp对应的实际输出Op
4.2.2计 算出Ep
4.2.3E=E+Ep
4.2.4 根据相应式子调整W^(L)
4.2.5 k=L-1
4.2.6while k!=0 do
4.2.6.1 根据相应的式子调整W^(k)
4.2.6.2 k=k-1

4.3e=e/2

The corresponding formulas mentioned in the algorithm flow can be used to use the artificial neural network (Artificial neural netwroks) notes-delta The Delta rules of the learning of rules

Basic BP algorithm "preference" after the sample, so that the subsequent sample on the network has a greater impact, how can improve this place?