Close the performance gap for available strategy

[AndreaCossu]

Currently, we still face a performance gap for some of the existing strategies.
The expected performance can be found in the comments of the related experiments folder.

Any help in closing the gap is welcome. Just comment this issue and I will assign you to that strategy.

List of strategies to "fix":

• Elastic Weight Consolidation on Permuted MNIST
• Synaptic Intelligence on Permuted MNIST
• iCarl on Split CIFAR-100
• RWalk on Split MNIST
• GSS on Split MNIST
• COPE on Split MNIST (most likely a bug on COPE)
• LaMAML on Split Tiny-ImageNet