An Overview on Effectiveness of Activation Functions in Processing Medical Images

Abstract

This study studies the impact of activation functions in the field of machine learning and
deep learning in general and especially on medical images for different aims such as classification,
clustering, feature engineering. Important components that add nonlinearity and allow networks to learn
intricate patterns are activation extraction, training and etc. The study first starts by explaining various
activation function types that are commonly used in NN applications and fields. Subsequently, a
comprehensive comparative analysis is conducted, to evaluate how activation functions perform in terms
of accuracy and their impact on speed convergence. Understanding how activation functions impact the
categorization of medical imagery is crucial to the study's findings. In additions, the study illustrates
overview of which activation functions yield optimal results. The Main results contribute how to select best
activation functions that suits most accurate and efficient medical image classification based on this
overview, any researcher can choose best activation function after reading this overview.