[object Object]

[object Object][object Object]undefined[object Object]

• Description: Performs backpropagation of .

• Formula:

  Computes the derivative of the activation function:

  $$\frac{\partial selu(x)}{\partial x}=\begin{cases} \alpha e^x,x<0 \\1,x\geq 0\end{cases}$$

  Computes the derivative of the error to the input:

  $$\frac{\partial E}{\partial x}=\frac{\partial E}{\partial y}\frac{\partial selu(x)}{\partial x}$$

  $y$ is the output, and $E$ is the loss function. $\alpha$=1.6732632423543772848170429916717

[object Object]

Each operator has calls. First, aclnnSeluBackwardGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnSeluBackward is called to perform computation.

[object Object]

• Parameters:

  [object Object]
  • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: The data type can be FLOAT, FLOAT16, INT32, or INT8.

• Returns:

  [object Object]: status code. For details, see .

  The first-phase API implements input parameter verification. The following errors may be thrown:

  [object Object]

[object Object]

• Parameters:

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

[object Object]

• Deterministic compute:
  • aclnnSeluBackward defaults to a deterministic implementation.

[object Object]

The following example is for reference only. For details, see .