Artificial intelligence models are increasingly common in many aspects of everyday life, not only in the most emblematic cases, but also in everyday cases such as recommendation systems on shopping websites. In this sense, developers need to understand how these models work. However, the massive use of libraries to use these models can hinder this understanding. Therefore, this work defines and formally demonstrates activation functions in machine learning models. This is a fundamental point for introducing the subject to new developers, and scientists, who will work in the area. The formal description applies to the classic ReLU, Sigmóide, hyperbolic tangent, softmax and gradient descent functions. In addition, the impact of these functions on the LeNet-5 model applied to the MNIST database is also discussed.

@article{Assuncao_Leal_2025,
title={Descrição formal das funções de ativação de modelos de aprendizado de máquina},
volume={6},
url={https://sistemas.uft.edu.br/periodicos/index.php/AJCEAM/article/view/20786},
DOI={10.20873/uft.2675-3588.2025.v6n1.p9-18},
number={1},
journal={Academic Journal on Computing, Engineering and Applied Mathematics},
author={Assunção Leal, Julia},
year={2025},
month={mar.},
pages={9–18}
}