A New Activation Function for Artificial Neural Net Based Habitability Classification

TitleA New Activation Function for Artificial Neural Net Based Habitability Classification
Publication TypeConference Paper
Year of Publication2018
AuthorsSaha, S.., A.. Mathur, K.. Bora, S.. Basak, and S.. Agrawal
Conference Name7th International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018
Date Published2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN Number9781538653142 (ISBN)
KeywordsActivation function, Activation functions, Analytical properties, Artificial neural net, Artificial neural networks, AstroInformatics, Calculations, Chemical activation, Different class, Exo-planets, exoplanets, Extrasolar planets, Learning systems, Local oscillation, Machine Learning, Neural networks, New activation functions
Abstract

We explore the efficacy of using a novel activation function in Artificial Neural Networks (ANN) in characterizing exoplanets into different classes. We call this Saha-Bora Activation Function (SBAF) as the motivation is derived from long standing understanding of using advanced calculus in modeling habitability score of Exoplanets. The function is demonstrated to possess nice analytical properties and doesn't seem to suffer from local oscillation problems. The manuscript presents the analytical properties of the activation function and the architecture implemented on the function. © 2018 IEEE.

URLhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85060007274&doi=10.1109%2fICACCI.2018.8554460&partnerID=40&md5=e2689fdc5323103919a6e2ce422d1729