Hard Sigmoid

2000년 도입 · 논문 4편에서 사용

The Hard Sigmoid is an activation function used for neural networks of the form: $$f\left(x\right) = \max\left(0, \min\left(1,\frac{\left(x+1\right)}{2}\right)\right)$$ Image Source: Rinat Maksutov

출처: BinaryConnect: Training Deep Neural Networks with binary weights during propagations

소개 논문: BinaryConnect: Training Deep Neural Networks with binary weights during propagations