Don't Fear Peculiar Activation Functions: EUAF and Beyond
This addresses bottlenecks in developing scalable and practical super-expressive activation functions for machine learning applications, though it appears incremental by generalizing an existing family.
The paper tackles the limited identification and peculiar forms of super-expressive activation functions by proposing the Parametric Elementary Universal Activation Function (PEUAF), demonstrating its effectiveness through experiments on datasets like CIFAR10, Tiny-ImageNet, and ImageNet.
In this paper, we propose a new super-expressive activation function called the Parametric Elementary Universal Activation Function (PEUAF). We demonstrate the effectiveness of PEUAF through systematic and comprehensive experiments on various industrial and image datasets, including CIFAR10, Tiny-ImageNet, and ImageNet. Moreover, we significantly generalize the family of super-expressive activation functions, whose existence has been demonstrated in several recent works by showing that any continuous function can be approximated to any desired accuracy by a fixed-size network with a specific super-expressive activation function. Specifically, our work addresses two major bottlenecks in impeding the development of super-expressive activation functions: the limited identification of super-expressive functions, which raises doubts about their broad applicability, and their often peculiar forms, which lead to skepticism regarding their scalability and practicality in real-world applications.