Add momentum to SGD trainer

[hughperkins]

• currently SGD training is implemented, with a learning rate and an annealed learning rate
• it could be good to add momentum

[hughperkins]

Started work on this, in 'momentum' branch. https://github.com/hughperkins/DeepCL/tree/momentum

[hughperkins]

So, I'm thinking about how this would work / be used.

Maybe something like, on the commandline one has an option like trainer=sgd, which at the moment would have the only one possible option, ie sgd, but in the future could change.

Then, depending on which trainer is chosen, additional options could be available, eg momentum, learningrate etc, and these would be handed to the sgd somehow.

I seem to have created a layer-specific sgd class, that has to be attached to each conv and fc layer, twice actually, once for biases, and once for non-biases, but this can be done simply by the commandline parser, ie:

1. set up the network
2. add appropriate trainer to each weighted layer

[hughperkins]

Done :-) In master branch.