<p>Segment-wise linear approximation of sigmoid(<aclass="reference external"href="https://arxiv.org/abs/1603.00391">https://arxiv.org/abs/1603.00391</a>),
which is much faster than sigmoid.</p>
<p>$out = max(0, min(1, slope * x + shift))$</p>
<p>The slope should be positive. The offset can be either positive or negative.
The default slope and shift are set according to the above reference.
It is recommended to use the defaults for this activation.</p>
<p>Segment-wise linear approximation of sigmoid(<aclass="reference external"href="https://arxiv.org/abs/1603.00391">https://arxiv.org/abs/1603.00391</a>),
which is much faster than sigmoid.</p>
<p>$out = max(0, min(1, slope * x + shift))$</p>
<p>The slope should be positive. The offset can be either positive or negative.
The default slope and shift are set according to the above reference.
It is recommended to use the defaults for this activation.</p>