Caffe_Activation_and_Neural

1. ReLU / Rectified-Linear and Leaky-ReLU - ReLU and LeakyReLU rectification.
2. PReLU - parametric ReLU.
3. ELU - exponential linear rectification.
4. Sigmoid
5. TanH
6. Absolute Value
7. Power - f(x) = (shift + scale * x) ^ power.
8. Exp - f(x) = base ^ (shift + scale * x).
9. Log - f(x) = log(x).
10. BNLL - f(x) = log(1 + exp(x)).
11. Threshold - performs step function at user defined
threshold.
12. Bias - adds a bias to a blob that can either be learned
or fixed.
13. Scale - scales a blob by an amount that can either be
learned or fixed.