Regularization Activation Function for Extreme Learning Machine
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 3
Abstract
Extreme Learning Machine (ELM) algorithm based on single hidden layer feedforward neural networks has shown as the best time series prediction technique. Furthermore, the algorithm has a good generalization performance with extremely fast learning speed. However, ELM facing overfitting problem that can affect the model quality due to the implementation using empirical risk minimization scheme. Therefore, this study aims to improve ELM by introducing an Activation Functions Regularization in ELM called RAF-ELM. The experiment has been conducted in two phases. First, investigating the modified RAF-ELM performance using four type of activation functions which is Sigmoid, Sine, Tribas and Hardlim. In this study, input weight and bias for hidden layers are randomly selected, whereas the best neurons number of hidden layer is determined from 5 to 100. This experiment used UCI benchmark datasets. The number of neurons (99) using Sigmoid activation function shown the best performance. The proposed methods has improved the accuracy performance and learning speed up to 0.016205 MAE and processing time 0.007 seconds respectively compared with conventional ELM and has improved up to 0.0354 MSE for accuracy performance compare with state of the art algorithm. The second experiment is to validate the proposed RAF-ELM using 15 regression benchmark dataset. RAF-ELM has been compared with four neural network techniques namely conventional ELM, Back Propagation, Radial Basis Function and Elman. The results show that RAF-ELM technique obtain the best performance compared to other techniques in term of accuracy for various time series data that come from various domain.
Authors and Affiliations
Noraini Ismail, Zulaiha Ali Othman, Noor Azah Samsudin
Keywords
Related Articles
- EP ID EP498526
- DOI 10.14569/IJACSA.2019.0100331
- Views 85
- Downloads 0
Modeling Access Control Policy of a Social Network
Social networks bring together users in a virtual platform and offer them the ability to share -within the Community- personal and professional information’s, photos, etc. which are sometimes sensitive. Although, the maj...
Dynamic Crypto Algorithm for Real-Time Applications DCA-RTA, Key Shifting
The need for fast and attack resistance crypto algorithm is challenging issue in the era of the revolution in the information and communication technologies. The previous works presented by the authors “Dynamic Crypto Al...
A Review on Urdu Language Parsing
Natural Language Processing is the multidisciplinary area of Artificial Intelligence, Machine Learning and Computational Linguistic for processing human language automatically. It involves understanding and processing of...
Development of Duck Diseases Expert System with Applying Alliance Method at Bali Provincial Livestock Office
Farming is one of the activities that have a business opportunity. One is raising ducks. The main results can be obtained from the breeding duck is a duck meat and eggs for consumption and also means praying ceremony in...
Automatic Construction of Java Programs from Functional Program Specifications
This paper presents a novel approach to construct Java programs automatically from the input functional program specifications on natural numbers from the constructive proofs of the input specifications using an inductiv...