The Adaptive Quadratic Linear Unit (AQuLU): Adaptive Non Monotonic Piecewise Activation Function

TEHNICKI VJESNIK-TECHNICAL GAZETTE(2023)

引用 0|浏览3
暂无评分
摘要
The activation function plays a key role in influencing the performance and training dynamics of neural networks. There are hundreds of activation functions widely used as rectified linear units (ReLUs), but most of them are applied to complex and large neural networks, which often have gradient explosion and vanishing gradient problems. By studying a variety of non-monotonic activation functions, we propose a method to construct a non-monotonic activation function, x center dot phi( x), with phi(x)is an element of[0, 1]. With the hardening treatment of phi(x), we propose an adaptive non-monotonic segmented activation function, called the adaptive quadratic linear unit, abbreviated as AQuLU, which ensures the sparsity of the input data and improves training efficiency. In image classification based on different state-of-the-art neural network architectures, the performance of AQuLUs has significant advantages for more complex and deeper architectures with various activation functions. The ablation experimental study further validates the compatibility and stability of AQuLUs with different depths, complexities, optimizers, learning rates, and batch sizes. We thus demonstrate the high efficiency, robustness, and simplicity of AQuLUs.
更多
查看译文
关键词
activation function, AQuLU, CaLU, deep learning, ExpExpish, LogLogish, LaLU
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要