Skip to main content
. 2019 Mar 5;19(5):1112. doi: 10.3390/s19051112

Table 1.

The code of the BP neural network algorithm.

Algorithm 1: The back propagation neural network
Definition:
Input layer neurons xi; The number of input layer neurons n; The hidden layer neurons Hj, H′j and H″j; The number of input layer neurons k; The output layer neurons y
Deposition
Initialization:
Initialize all weights and biases in network;
for i=1 to n do
 Create hierarchy model and assign to neurons x8=(fs, fh, p, ns, t, h, ws, v); y=(d)
 xi = X(xi)
end
forj=1 tokdo
 fort=1 to 3 do
  Hj←ΣWijxi+bj
  H′j←ΣW’ijHj+b’j
  H″j←ΣW″ijH′j+b″j
  yo←g(H″j)
 end
end
for all j in k do
 E←1/2Σej2
 if (E ∉ Error) do
  Wij←Wij+αHjej
  bj←bj+βej
 return i=1
 else y=yo
End