Skip to main content

Table 1 The relation between the neural network and separation process

From: A MLE-based blind signal separation method for time–frequency overlapped signal using neural network

NN layer

Dimension

Information

Input layer

\(M+1\)

Observation \({\textbf{x}}\) and initial bias term b

Dense layer

D

Optimization Parameters: \({\textbf{W}}\) and b

Lambda layer

2

Cost function as Eq. (19)

Output layer

1

Loss value