- namespace: Rindow\NeuralNetworks\Gradient\Func
- classname: Equal
Compare each element of the array; if the values are the same, it becomes 1, and if they are different, it becomes 0.
This is a non-backpropagable function.
Methods
equal
$g->equal(
Variable|NDArray $a,
Variable|NDArray $b
) : Variable
Create and execute the function in the builder method
Arguments
- a,b: The arguments are Variable or NDArray. Implicitly create Variable for NDArray.
use Rindow\Math\Matrix\MatrixOperator;
use Rindow\NeuralNetworks\Builder\NeuralNetworks;
$mo = new MatrixOperator();
$nn = new NeuralNetworks($mo);
$g = $nn->gradient();
$a = $g->Variable([1,2]);
$b = $g->Variable([3,2]);
$c = $nn->with($tape=$g->GradientTape(),function() use ($g,$a,$b) {
return $g->equal($a,$b);
});
echo $mo->toString($c)."\n";