Scaling dropout layer by keep probability during test time

[Chris-Nicholls]

From the dropout paper http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf :

If a unit is retained with probability p during training, the outgoing weights of that unit are multiplied by p at test time

The test activations should be scaled by (1-drop_prob), not drop_prob.
For example, if drop prob is 0, this layer should have no effect and we should scale activations by 1.

[ratajczak]

Hi Chris, it looks like duplicate of #61

[Chris-Nicholls]

Yup, you're right. Looks like this isn't being maintained anyway.