class BinarySigmoid
-
class BinarySigmoid
Elementwise BinarySigmoid function defined as.
\[\begin{split} y_i = \left \{ \begin{array}{ll} 1 & (x_i > 0)\\ 0 & (x_i \leq 0) \end{array} \right.. \end{split}\]Inputs:
N-D array.
Outputs:
N-D array.
See also
Courbariaux, Matthieu, and Yoshua Bengio. Binarynet: Training deep neural networks with weights and activations constrained to+ 1 or-1. preprint arXiv:1602.02830 (2016).
- Template Parameters:
T – Data type for computation.