* Implemented the hardShrink activation

* Fixing the unit test

* Add numerically-stable logsigmoid activation

* Add softshrink operator

* Adjust relative tolerance for grad-check

* Address review comments

* conv_shift_op: initial implementation using Eigen

Limitations:
- both gradient outputs must be specified and are always computed
- explicit for loops => could be optimized in various ways
  (e.g., different memory layout)

* conv shift - gradient fixes

fix case when not all output gradients desired

* conv shift: minor cleanup

* conv shift - more minor cleanup

* conv shift: clean up & initial GPU implementation

* fix rebase issue

It will significantly reduce binary size. It is useful for mobile
deployment.

* Implementing the Adamax optimizer step operator
* Adding unit tests for adamax_op

* Changing learning rate and time step to inputs from attributes

* Changing learning rate and time step to input(tensors)

* Making the Adamax operator conform to naming convention

* Removing Tensor<float> from comments

* Rectifying the Adamax implementation

* Changing Unit Test values and adding comments

* Changing Unit Test to test multiple steps

* Adding Adadelta optimization operator
* Making inputs and outputs conform to naming convention
* Removing type alias from header files
* Fixing Adadelta documentation in comments
* Addressing code review feedback

By shell command

```bash
sed -i 's#ifdef PADDLE_ONLY_CPU#ifndef PADDLE_WITH_GPU#g' `find ./paddle/ -name '*.h' -o -name '*.cc' -o -name '*.cpp' -o -name '*.c' -o -name '*.cu'`
sed -i 's#ifndef PADDLE_ONLY_CPU#ifdef PADDLE_WITH_GPU#g' `find ./paddle/ -name '*.h' -o -name '*.cc' -o -name '*.cpp' -o -name '*.c' -o -name '*.cu'`
```

* Changing learning rate from attribute to input(float)
* Removing obsolete code