We need this operator to assign value to a tensor and the values are stored in the program so that they can be used independent of python.

Added backward.calc_gradient to backpropagate gradient from given targets to inputs.

* Add squared error layers doc

* Add doc for gru_unit

* Remove cdot which isn't supported

* Update layers.rst

* Update layers.rst (minor)

x_num_col_dims => num_flatten_dims

* Addign document for fluid split_lod_tensor

* Adding document for fluid merge_lod_tensor