Artificial neural Network (Artificial neural netwroks) Note--Training algorithm of discrete multi-output perceptron

This is an extension of the discrete single output perceptron algorithm

Related symbolic definitions refer to the artificial neural network (Artificial neural netwroks) Note-discrete single output perceptron algorithm

Ok,start our Game

1. Initialization weight matrix W;

2. Repeat the following process until the training is complete:

2.1 For each sample (X,y), repeat the following procedure:

2.1.1 Input x;

2.1.2 Calculation o=f (XW);

2.1.3 for J=1 to M does the following:

if　Oj != Yj then
if Oi=0 then for i=1 to　n
Wij=Wij+Xi
else for i=1 to n do
Wij=Wij-Xi

Where the O=f (XW) represents the output by activating the function, this explains