Skip to main content

Table 4 Model-specific hyperparameters for comparison a dense Layer network ReLu vs. a LONN

From: Medical recommender systems based on continuous-valued logic and multi-criteria decision operators, using interpretable neural networks

  NN–dense layers/ReLU activation LONN
\(\beta _{{int}}\) 1.5
Learning rate (lr) 0.02 0.02
# Internal layers 4 4
# Neurons per layer 10, 4, 3, 2 10, 4, 3, 2
# Trainable parameters 293 116
# Non-trainable parameters 0 59