Open wehlutyk opened 6 years ago
None of these are necessary, I'm just listing them to keep track of all the possible small-ish changes that might improve performance or reduce the need for resources:
Normalizations:
Connections:
Reduction of necessary parameters and resources:
Noise for training:
Removing unneeded left-overs:
Different models:
How Powerful are Graph Neural Networks? uses batch-normalisation at all layers.
None of these are necessary, I'm just listing them to keep track of all the possible small-ish changes that might improve performance or reduce the need for resources:
Normalizations:
Connections:
Reduction of necessary parameters and resources:
Noise for training:
Removing unneeded left-overs:
Different models: