vmlsmht - SMHT activation

4.29 vmlsmht - SMHT activation

#include <mvecml.h> 
 
void vmlsmht(int n, double *restrict y, int incy, 
             double a, double b, double c, double d, const double *restrict x, int incx); 
void vmlsmhtf(int n, float *restrict y, int incy, 
              float a, float b, float c, float d, const float *restrict x, int incx); 
 
void vmlsmht_64(long n, double *restrict y, long incy, 
                double a, double b, double c, double d, const double *restrict x, long incx); 
void vmlsmhtf_64(long n, float *restrict y, long incy, 
                 float a, float b, float c, float d, const float *restrict x, long incx);

Given an input vector $x$ , a result vector $y$ and constants $λ$ and $α$ this function computes the Soboleva modified hyperbolic tangent (SMHT) activation function of the values in the $x$ vector and stores the result in the $y$ vector.

.eax-e-bx y= ecx+e-dx

4.29.1 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.
A - REAL: ENTRY: Constant $a$ .
B - REAL: ENTRY: Constant $b$ .
C - REAL: ENTRY: Constant $c$ .
D - REAL: ENTRY: Constant $d$ .
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.

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