func_grad: Compute Function Gradient
In joeddav/CNTK-R: R Interface to the Microsoft Cognitive Toolkit (CNTK)

Computes the gradient of this Function at location at with respect to wrt. The Function must have a single output.

1 2	func_grad(func, at, wrt = NULL, outputs = NULL, device = NULL, as_matrix = TRUE, grad_root = NULL)

`func`	- The CNTK 'Function' instance on which to apply the operation
`at`	- mapping of the Function’s arguments to values
`wrt`	- list of Variables with respect to which the gradient will be computed. If omitted, the gradients with respect to all arguments of this Function that need gradient will be computed.
`device`	- instance of DeviceDescriptor
`as_matrix`	- whether to return as an R matrix. Defualt TRUE. Otherwise returns as Python CNTK value which avoids costly conversions
`grad_root`	- specify the root of gradients calculation. If not specified, the output of this function will be used as gradient root.