IEEE

Curvature-Based Piecewise Linear Approximation Method of GELU Activation Function in Neural Networks

Abstract: Artificial neural networks (ANNs) rely significantly on activation functions for optimal performance. Traditional activation functions such as ReLU and Sigmoid are commonly used. However, ...
IEEE

Solving Sparse Linear Inverse Problems in Communication Systems: A Deep Learning Approach With Adaptive Depth

Abstract: Sparse signal recovery problems from noisy linear measurements appear in many areas of wireless communications. In recent years, deep learning (DL) based approaches have attracted interests ...