NDLI: Modified Neural Network Activation Function

Content Provider	IEEE Xplore Digital Library
Author	Abubakar, A.I. Chiroma, H. Abdulkareem, S. Gital, A.Y. Muaz, S.A. Maitama, J. Isah, M.L. Herawan, T.
Copyright Year	2014
Description	Author affiliation: Dept. of Math. Scinece, Abubakar Tafawa Balewa Univ., Bauchi, Nigeria (Gital, A.Y.) \|\| Dept. of Software Eng., Univ. of Malaya, Kuala Lumpur, Malaysia (Muaz, S.A.; Maitama, J.) \|\| Dept. of Inf. Syst., Univ. of Malaya, Kuala Lumpur, Malaysia (Herawan, T.) \|\| Dept. of Inf. Syst., Int. Islamic Univ. Malaysia, Kuala Lumpur, Malaysia (Abubakar, A.I.) \|\| Dept. of Artificial Intell., Univ. of Malaya, Kuala Lumpur, Malaysia (Chiroma, H.; Abdulkareem, S.) \|\| Dept. of Comput. Sci., Abubakar Tatari Ali Polytech. Bauchi, Bauchi, Nigeria (Isah, M.L.)
Abstract	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.
Starting Page	8
Ending Page	13
File Size	120137
Page Count	6
File Format	PDF
e-ISBN	9781479979103
DOI	10.1109/ICAIET.2014.12
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-12-03
Publisher Place	Malaysia
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Training Support vector machines Artificial Neural Network; Activation Function; Training algorithm; Logsig; Hyperbolic Neurons Artificial neural networks Artificial intelligence Biological neural networks Analysis of variance
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Crucial Data Selection Based on Random Weight Neural Network

Decision boundary learning based on particle swarm optimization

A benchmark study regarding Extreme Learning Machine, modified versions of Naïve Bayes Classifier and Fast Support Vector Classifier

Reducing neural network training data using support vectors

ANNEbot: An evolutionary artificial neural network framework

CSIA: a basis for constructing agent brains

Airport unexploded ordnances identification based on artificial neural network and fuzzy support vector machines

A modified version of a formal pruning algorithm based on local relative variance analysis

Learning architectures with enhanced capabilities and easier training

Modified Neural Network Activation Function

Similar Documents

Crucial Data Selection Based on Random Weight Neural Network

Decision boundary learning based on particle swarm optimization

A benchmark study regarding Extreme Learning Machine, modified versions of Naïve Bayes Classifier and Fast Support Vector Classifier

Reducing neural network training data using support vectors

ANNEbot: An evolutionary artificial neural network framework

CSIA: a basis for constructing agent brains

Airport unexploded ordnances identification based on artificial neural network and fuzzy support vector machines

A modified version of a formal pruning algorithm based on local relative variance analysis

Learning architectures with enhanced capabilities and easier training

Modified Neural Network Activation Function