Skip to main content

Table 2 Hyperparameters of interest for the proposed DU-PDA

From: Low-complexity deep unfolded neural network receiver for MIMO systems based on the probability data association detector

Hyperparameters Values
Training set size \(10^5\) samples
Layers \(L = 4N_t\)
Input dimension \({\mathbb {R}}^{2N_r}\text {,} \ {\mathbb {R}}^{2N_r \times 2N_t}\text {,} \ {\mathbb {R}}^{2N_t \times \sqrt{M}}\text {,} \ {\mathbb {R}}^{2N_t}\)
Output dimension \({\mathbb {R}}^{2N_t \times \sqrt{M}}\)
Number of  
learnable \(\#\{w_\ell \}_{\forall \ell } = 4N_t\)
Activation function \(\text {softmax}\left( \cdot \right) , \ \forall \ell\)
Learning rate \(10^{-3}\)
Solver Adam