SMU: smooth activation function for deep networks using smoothing maximum technique
This work addresses the need for better activation functions in deep learning, offering a domain-specific improvement for neural network models.
The authors tackled the problem of improving deep network performance by proposing a new activation function called Smooth Maximum Unit (SMU), which approximates known functions like Leaky ReLU, and achieved a 6.22% improvement on the CIFAR100 dataset with ShuffleNet V2.
Deep learning researchers have a keen interest in proposing two new novel activation functions which can boost network performance. A good choice of activation function can have significant consequences in improving network performance. A handcrafted activation is the most common choice in neural network models. ReLU is the most common choice in the deep learning community due to its simplicity though ReLU has some serious drawbacks. In this paper, we have proposed a new novel activation function based on approximation of known activation functions like Leaky ReLU, and we call this function Smooth Maximum Unit (SMU). Replacing ReLU by SMU, we have got 6.22% improvement in the CIFAR100 dataset with the ShuffleNet V2 model.