* initial matmul operator

Similar to np.matmul, but also has transpose_X and transpose_Y flags,
and only supports tensors from rank 1 to 3 inclusive.

For GPU, uses cublas?gemmStridedBatched. For CPU, uses
cblas_?gemm_batch if available via MKL; otherwise a simple serial
implementation that loops over the batch dimension is employed for now.

* 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

Make implement an operator less noisy.

* a simplest SGD op