激活函数:Swish: a Self-Gated Activation Function

今天看到google brain 关于激活函数在2017年提出了一个新的Swish 激活函数。

叫swish,地址:https://arxiv.org/abs/1710.05941v1 

pytorch里是这样的:

def relu_fn(x):

    """ Swish activation function """

    return x * torch.sigmoid(x)

 Swish, which is simply f(x) = x ·sigmoid(x). Our experiments show that Swish tends to work better than ReLU on deeper models across a number of challenging datasets.

For example, simply replacing ReLUs with Swish units improves top-1 classification accuracy on ImageNet by0.9% for MobileNASNetA and 0.6% for Inception-ResNet-v2.

The simplicity of Swish and its similarity to ReLU make it easy for practitioners to replace ReLUs with Swish units in any neural network.

激活函数:Swish: a Self-Gated Activation Function_第1张图片

他人的介绍:

https://blog.csdn.net/wydbyxr/article/details/84615522

 

转载于:https://www.cnblogs.com/yjphhw/p/11083877.html

你可能感兴趣的:(激活函数:Swish: a Self-Gated Activation Function)