vmlgelud - GELU activation (first derivative)

Math Vector Library Machine Learning Extension
Programming Reference Manual Fortran
Version 1.0 DD-00004-110

4.12 vmlgelud - GELU activation (first derivative)

subroutine vmlgelud (n, y, incy, x, incx);
subroutine vmlgeludf(n, y, incy, x, incx);

Given an input vector $x$ and a result vector $y$ this function computes the first derivative of the GELU activation function of the values in the $x$ vector and stores the result in the $y$ vector.

( ( )) y .= 1 x 1+erf ⎷x + ⎷-x⎷--e-x2/2 2 2 2 π

4.12.1 Parameters

N - INTEGER: ENTRY: Number of elements of $x$ and $y$ .
CONSTRAINT: $n ≥1$ .
Y - ARRAY OF REAL: EXIT: Result vector $y$ .
CONSTRAINT: Must contain $n× incy$ elements.
CONSTRAINT: Must not overlap with array $x$ .
INCY - INTEGER: ENTRY: Stride for the vector $y$ .
CONSTRAINT: $incy> 0$ .
X - ARRAY OF REAL: ENTRY: Input vector $x$ .
CONSTRAINT: Must contain $n× incx$ elements.
CONSTRAINT: Must not overlap with array $y$ .
INCX - INTEGER: ENTRY: Stride for the vector $x$ .
CONSTRAINT: $incx> 0$ .

[next] [prev] [prev-tail] [front] [up]