Remove momentum from Layers

[HuwCampbell]

• Momentum shouldn't be stored in the layers any more. This will free us up to use a broader set of optimisation algorithms. We will however need to provide a class for fast updates and manipulations of learnable parameters.

• Gradient associated type family shouldn't exist, we'll just return a Network with gradient weights.

• randomNetwork shouldn't exist. Networks where all layers have a Random instance will also have a Random instance.

[claudeha]

Moreover, I noticed momentum is not serialized, which means saving/resuming training between sessions may be problematic.

[HuwCampbell]

Indeed.