Weighted Sigmoid Gate Unit for an Activation Function of Deep Neural Network
This work addresses the need for better activation functions in deep learning, offering incremental improvements for tasks such as object recognition and image restoration.
The paper tackles the problem of improving activation functions in deep neural networks by proposing a weighted sigmoid gate unit (WiG), which outperforms existing functions like ReLU in object recognition and image restoration tasks.
An activation function has crucial role in a deep neural network. A simple rectified linear unit (ReLU) are widely used for the activation function. In this paper, a weighted sigmoid gate unit (WiG) is proposed as the activation function. The proposed WiG consists of a multiplication of inputs and the weighted sigmoid gate. It is shown that the WiG includes the ReLU and same activation functions as a special case. Many activation functions have been proposed to overcome the performance of the ReLU. In the literature, the performance is mainly evaluated with an object recognition task. The proposed WiG is evaluated with the object recognition task and the image restoration task. Then, the expeirmental comparisons demonstrate the proposed WiG overcomes the existing activation functions including the ReLU.