An Empirical Study of Activation Functions for Function Approximation Tasks

Autor:	Pravin Chandra, Udayan Ghose, Apoorvi Sood
Rok vydání:	2021
Předmět:	Class (set theory) Function approximation Empirical research Artificial neural network Generalization Activation function Applied mathematics Sigmoid function Unit (ring theory) Mathematics
Zdroj:	Lecture Notes in Networks and Systems ISBN: 9789811597114
DOI:	10.1007/978-981-15-9712-1_24
Popis:	Activation functions play a major role in determining the learning speed and generalization capability of feed-forward artificial neural networks. In this paper, an empirical comparison of eight activation functions is reported on 12 function approximation problems. The study allows us to assert that the sigmoidal class of activation functions performed much better than the non-sigmoidal class of activation functions. Out of the six non-sigmoidal activation function, one activation function called the sigmoidal-weighted linear unit is identified as outperforming all other non-sigmoidal activation functions.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::43d536f9d3614681d26c11d2fd9aef6e https://doi.org/10.1007/978-981-15-9712-1_24 Zobrazit plný text záznamu