Year: 2024
Type: preprint
Abstract: A general procedure for introducing parametric, learned, nonlinearity into activation functions is found to enhance the accuracy of representative neural networks without requiring significant additional computational resources. Examples are given based on the standard rectified linear unit (ReLU) as well as several other frequently employed activation functions. The associated accuracy improvement is quantified both in the context of the MNIST digit data set and a convolutional neural network (CNN) benchmark example.
Source: arXiv (Cornell University)
Author: Yevick, David
Institution: University of Waterloo
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4393399162