Skip to main content

Advertisement

Table 1 Layers of classifier neural network

From: A machine-learning phase classification scheme for anomaly detection in signals with periodic characteristics

  Layer Type Sizes
0 Convolutional M(0)=d, T(0)=T,
   S(0)=(T/6+1)·2+1
1 Max pooling M(1)=M(0)·6, T(1)=T(0),
   R(1)=3 if applicable, else R(1)=1
2 Convolutional M(2)=M(1), T(2)=T(1)/R(1),
   S(2)=(T/12+1)·2+1
   M(3)=M(2)·3, T(3)=T(2)
3 Fully connected N(3)=M(3)·T(3)
4 Fully connected \(N^{(4)} = \lfloor \sqrt {N^{(3)} \cdot N^{(5)}} \rfloor \)
5 Output N(5)=n