Math Vector Library 1.1 Machine Learning Extension
Programming Reference Manual Fortran
Version 1.1 DD-00004-111

4.27 vmlselu - SELU activation

subroutine vmlselu (n, y, incy, l, a, x, incx); 
subroutine vmlseluf(n, y, incy, l, a, x, incx); 
 
subroutine vmlselu_64 (n, y, incy, l, a, x, incx); 
subroutine vmlseluf_64(n, y, incy, l, a, x, incx);

Given an input vector x  , a result vector y  and constants λ and α this function computes the SELU activation function of the values in the x  vector and stores the result in the y  vector.

    {
 .   α(ex-1)  wherex <0
y= λ x        wherex ≥0

4.27.1 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: incy̸= 0  .
BEHAVIOR: A negative stride will traverse the array in reverse.

L - REAL

ENTRY: Constant λ .

A - REAL

ENTRY: Constant α .

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: incx̸= 0  .
BEHAVIOR: A negative stride will traverse the array in reverse.