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 |