Modified neural network activation function

Neural Network is said to emulate the brain, though, its processing is not quite how the biological brain really works. The Neural Network has witnessed significant improvement since 1943 to date. However, modifications on the Neural Network mainly focus on the structure itself, not the activat...

Full description

Bibliographic Details
Main Authors: Ibrahim, Adamu Abubakar, Chiroma, Haruna, Abdulkareem, Sameem, Ya’u Gital, Abdulsalam, Abdullahi Muaz, Sanah, Maitama, Jafaar, Isah, Muhammad Lamir, Herawan, Tutut
Format: Proceeding Paper
Language:English
English
Published: 2014
Subjects:
Online Access:http://irep.iium.edu.my/39658/
http://irep.iium.edu.my/39658/1/39658.pdf
http://irep.iium.edu.my/39658/4/39658_Modified%20Neural%20Network%20Activation%20Function.SCOPUS.pdf
_version_ 1848781827287810048
author Ibrahim, Adamu Abubakar
Chiroma, Haruna
Abdulkareem, Sameem
Ya’u Gital, Abdulsalam
Abdullahi Muaz, Sanah
Maitama, Jafaar
Isah, Muhammad Lamir
Herawan, Tutut
author_facet Ibrahim, Adamu Abubakar
Chiroma, Haruna
Abdulkareem, Sameem
Ya’u Gital, Abdulsalam
Abdullahi Muaz, Sanah
Maitama, Jafaar
Isah, Muhammad Lamir
Herawan, Tutut
author_sort Ibrahim, Adamu Abubakar
building IIUM Repository
collection Online Access
description Neural Network is said to emulate the brain, though, its processing is not quite how the biological brain really works. The Neural Network has witnessed significant improvement since 1943 to date. However, modifications on the Neural Network mainly focus on the structure itself, not the activation function despite the critical role of activation function in the performance of the Neural Network. In this paper, we present the modification of Neural Network activation function to improve the performance of the Neural Network. The theoretical background of the modification, including mathematical proof is fully described in the paper. The modified activation function is code name as SigHyper. The performance of SigHyper was evaluated against state of the art activation function on the crude oil price dataset. Results suggested that the proposed SigHyper was found to improved accuracy of the Neural Network. Analysis of variance showed that the accuracy of the SigHyper is significant. It was established that the SigHyper require further improvement. The activation function proposed in this research has added to the activation functions already discussed in the literature. The study may motivate researchers to further modify activation functions, hence, improve the performance of the Neural Network.
first_indexed 2025-11-14T15:55:45Z
format Proceeding Paper
id iium-39658
institution International Islamic University Malaysia
institution_category Local University
language English
English
last_indexed 2025-11-14T15:55:45Z
publishDate 2014
recordtype eprints
repository_type Digital Repository
spelling iium-396582018-05-23T06:35:40Z http://irep.iium.edu.my/39658/ Modified neural network activation function Ibrahim, Adamu Abubakar Chiroma, Haruna Abdulkareem, Sameem Ya’u Gital, Abdulsalam Abdullahi Muaz, Sanah Maitama, Jafaar Isah, Muhammad Lamir Herawan, Tutut Q350 Information theory Neural Network is said to emulate the brain, though, its processing is not quite how the biological brain really works. The Neural Network has witnessed significant improvement since 1943 to date. However, modifications on the Neural Network mainly focus on the structure itself, not the activation function despite the critical role of activation function in the performance of the Neural Network. In this paper, we present the modification of Neural Network activation function to improve the performance of the Neural Network. The theoretical background of the modification, including mathematical proof is fully described in the paper. The modified activation function is code name as SigHyper. The performance of SigHyper was evaluated against state of the art activation function on the crude oil price dataset. Results suggested that the proposed SigHyper was found to improved accuracy of the Neural Network. Analysis of variance showed that the accuracy of the SigHyper is significant. It was established that the SigHyper require further improvement. The activation function proposed in this research has added to the activation functions already discussed in the literature. The study may motivate researchers to further modify activation functions, hence, improve the performance of the Neural Network. 2014-12-03 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/39658/1/39658.pdf application/pdf en http://irep.iium.edu.my/39658/4/39658_Modified%20Neural%20Network%20Activation%20Function.SCOPUS.pdf Ibrahim, Adamu Abubakar and Chiroma, Haruna and Abdulkareem, Sameem and Ya’u Gital, Abdulsalam and Abdullahi Muaz, Sanah and Maitama, Jafaar and Isah, Muhammad Lamir and Herawan, Tutut (2014) Modified neural network activation function. In: 4th International Conference on Artificial Intelligence with Applications in Engineering and Technology (ICAIET 2014), 3 - 5th December, 2014, Kota Kinabalu, Sabah. http://uksim.info/icaiet2014/CD+ToC.pdf
spellingShingle Q350 Information theory
Ibrahim, Adamu Abubakar
Chiroma, Haruna
Abdulkareem, Sameem
Ya’u Gital, Abdulsalam
Abdullahi Muaz, Sanah
Maitama, Jafaar
Isah, Muhammad Lamir
Herawan, Tutut
Modified neural network activation function
title Modified neural network activation function
title_full Modified neural network activation function
title_fullStr Modified neural network activation function
title_full_unstemmed Modified neural network activation function
title_short Modified neural network activation function
title_sort modified neural network activation function
topic Q350 Information theory
url http://irep.iium.edu.my/39658/
http://irep.iium.edu.my/39658/
http://irep.iium.edu.my/39658/1/39658.pdf
http://irep.iium.edu.my/39658/4/39658_Modified%20Neural%20Network%20Activation%20Function.SCOPUS.pdf