Filters








12 Hits in 9.2 sec

A Global-best Harmony Search based Gradient Descent Learning FLANN (GbHS-GDL-FLANN) for data classification

Bighnaraj Naik, Janmenjoy Nayak, Himansu Sekhar Behera
2016 Egyptian Informatics Journal  
In this paper, a variant of Harmony Search (HS), called Global-best Harmony Search along with Gradient Descent Learning is used with Functional Link Artificial Neural Network (FLANN) for classification  ...  The proposed method (GbHS-GDL-FLANN) is implemented in MATLAB and compared with other alternatives (FLANN, GA based FLANN, PSO based FLANN, HS based FLANN, Improved HS based FLANN, Self Adaptive HS based  ...  In this paper, an attempted has been made to design a FLANN model with hybrid Global-best Harmony Search (GbHS) and Gradient descent search based learning method for classification.  ... 
doi:10.1016/j.eij.2015.09.001 fatcat:z2rlgho7sncojkc2wxtl6iy4bu

A novel nature inspired firefly algorithm with higher order neural network: Performance analysis

Janmenjoy Nayak, Bighnaraj Naik, H.S. Behera
2016 Engineering Science and Technology, an International Journal  
In this paper, a Firefly based higher order neural network has been proposed for data classification for maintaining fast learning and avoids the exponential increase of processing units.  ...  A memory based Sigma-Pi-Sigma neural network for excellent learning convergence along with reducing the memory size and overcoming the possible extensive memory requirement problem has been suggested by  ...  The authors would like to thank to the Editor and the reviewers for their valuable comments and suggestions that helped to improve the content of the paper in a large extent.  ... 
doi:10.1016/j.jestch.2015.07.005 fatcat:m6inqzai75bhngh6uh565nn5jq

Development and Performance Evaluation of Adaptive Hybrid Higher Order Neural Networks for Exchange Rate Prediction

Sarat Chandra Nayak
2017 International Journal of Intelligent Systems and Applications  
Nature-inspired optimization algorithms are capable of searching better than gradient descent-based search techniques.  ...  The efficiency of the models is compared with that of a Radial basis functional neural network, a multilayer perceptron, and a multi linear regression method and established their superiority.  ...  ACKNOWLEDGEMENT The author likes to thank anonymous reviewer(s) and the Chief Editor for their valuable comments and suggestions which have certainly improved the quality of this paper.  ... 
doi:10.5815/ijisa.2017.08.08 fatcat:tqobsmmdubeerkyj2xqoyqweum

A comprehensive survey on functional link neural networks and an adaptive PSO–BP learning for CFLNN

Satchidananda Dehuri, Sung-Bae Cho
2009 Neural computing & applications (Print)  
and breadth of the theory and applications; (2) present a new hybrid learning scheme for Chebyshev functional link neural network (CFLNN); and (3) suggest possible remedies and guidelines for practical  ...  We then validate the proposed learning scheme for CFLNN in classification by an extensive simulation study. Comprehensive performance comparisons with a number of existing methods are presented.  ...  The authors greatly appreciate all the reviewers' constructive comments that motivated them to think more and improve the presentation of this paper.  ... 
doi:10.1007/s00521-009-0288-5 fatcat:4x4oovm5r5htzeqymbbtt34n6a

Artificial Neural Networks Based Optimization Techniques: A Review

Maher G. M. Abdolrasol, S. M. Suhail Hussain, Taha Selim Ustun, Mahidur R. Sarker, Mahammad A. Hannan, Ramizi Mohamed, Jamal Abd Ali, Saad Mekhilef, Abdalrhman Milad
2021 Electronics  
This paper includes some results for improving the ANN performance by PSO, GA, ABC, and BSA optimization techniques, respectively, to search for optimal parameters, e.g., the number of neurons in the hidden  ...  layers and learning rate.  ...  A PSO combined with ANN for data classification with an opposition-based PSO neural network (OPSONN) algorithm was used for the NN training to solve data classification problems [133] .  ... 
doi:10.3390/electronics10212689 fatcat:oupnikhxdbhedfz5yeatmtj4xa

Cat Swarm Optimization Algorithm: A Survey and Performance Evaluation

Aram M. Ahmed, Tarik A. Rashid, Soran Ab. M. Saeed
2020 Computational Intelligence and Neuroscience  
CSO is a robust and powerful metaheuristic swarm-based optimization approach that has received very positive feedback since its emergence.  ...  The results are then compared against three novel and powerful optimization algorithms, namely, dragonfly algorithm (DA), butterfly optimization algorithm (BOA), and fitness dependent optimizer (FDO).  ...  Sarswat et al. also proposed a hybrid system by combining CSO, GA, and SA and then incorporating it with a modularity-based method [25] . ey named their algorithm hybrid CSO-GA-SA. e structure of the  ... 
doi:10.1155/2020/4854895 pmid:32405296 pmcid:PMC7204373 fatcat:yznuso5v45e37loko2tfxfgzy4

Artificial chemical reaction optimization of neural networks for efficient prediction of stock market indices

S.C. Nayak, B.B. Misra, H.S. Behera
2017 Ain Shams Engineering Journal  
The underlying system models of time series prediction are complex and not known a priori, hence, accurate and unbiased estimation cannot be always achieved using well known linear techniques.  ...  The underlying motivation for using ACRO is the ability to overcome the issues of convergence, parameter setting and overfitting and to accurately forecast financial time series data even when the underlying  ...  They used GA and Gradient Descent (GD) learning algorithm alternatively in an iterative manner to adjust the parameters and their results indicate that hybrid iterative evolutionary learning is more powerful  ... 
doi:10.1016/j.asej.2015.07.015 fatcat:6vfz4cj6xbg2lj2dwqjqt37cba

A Systematic Review on Harmony Search Algorithm: Theory, Literature, and Applications

Mahima Dubey, Vijay Kumar, Manjit Kaur, Thanh-Phong Dao, Hassène Gritli
2021 Mathematical Problems in Engineering  
The improvement and hybridization in HSA with other metaheuristics are discussed in detail. The applicability of HSA in different problem domains is studied.  ...  The natural inspiration and conceptual framework of HSA are discussed. The control parameters of HSA are described with their mathematical foundation.  ...  [40] proposed a variant of GHSA that utilized the concepts of gradient descent learning (GDL) and functional link artificial neural network (FLANN). e search capability of GDL was used to optimize the  ... 
doi:10.1155/2021/5594267 fatcat:dtpsvroglrf55mhgf4dypzbtki

Whale–crow optimization (WCO)-based Optimal Regression model for Software Cost Estimation

Sumera W Ahmad, G R Bamnote
2019 Sadhana (Bangalore)  
Regression model and 0.2692 for the proposed Kernel Regression model. adhana(0123456789().  ...  Analysis is carried out regarding the mean magnitude of relative error (MMRE) that proves that the proposed method of SCE is effective, attaining the average MMRE at a rate of 0.2442 for the proposed Linear  ...  The other methods, PSO-FCM, Tabu Search ? GA, PSOCP, the Linear Regression and the Kernel Regression, yield a greater value when compared with the optimization-based regressions.  ... 
doi:10.1007/s12046-019-1085-1 fatcat:kcw5mcvsobbotmarl2qsgovr2a

Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 [article]

Omer Berat Sezer, Mehmet Ugur Gudelek, Ahmet Murat Ozbayoglu
2019 arXiv   pre-print
Machine Learning (ML) researchers came up with various models and a vast number of studies have been published accordingly.  ...  Lately, Deep Learning (DL) models started appearing within the field, with results that significantly outperform traditional ML counterparts.  ...  The authors of [212] proposed a novel method that used text mining techniques and Hybrid Attention Networks based on financial news for the forecast of the trend of stocks.  ... 
arXiv:1911.13288v1 fatcat:npvyhewuvvcvri4e43jwj3c45y

Significant Feature Set Driven Enhanced Classification Significant Feature Set Driven and Optimized FFN for Enhanced Classification

Asha Gowda Karegowda, Sha Karegowda, M Jayaram
International Journal of Computational Intelligence and Informatics   unpublished
PSO showed best classification accuracy in the range of 86%-97% for all the datasets considered when compared with BPN and GA based networks.  ...  PSO showed best classification accuracy in the range of 86% considered when compared with BPN and GA based networks. T was also modest, with a few neurons in the hidden layer.  ...  In this paper, a novel classification scheme is elaborated. The method evolved has two y using decision tree and GA-CFS (genetic algorithm based correlation based feature selection).  ... 
fatcat:f3zwx5oej5g2tgrdxgh3m6gb3m

Parallel MCNN (pMCNN) with Application to Prototype Selection on Large and Streaming Data

V. Susheela Devi, Lakhpat Meena
2017 Journal of Artificial Intelligence and Soft Computing Research  
The results of these algorithms using MCNN and pMCNN have been compared with an existing algorithm for streaming data.  ...  To mitigate this, we propose a distributed approach called Parallel MCNN (pMCNN) which cuts down the time drastically while maintaining good performance.  ...  [21] proposed radial basis function neural network with two stage gradient descent strategy for partial differential equations.  ... 
doi:10.1515/jaiscr-2017-0011 fatcat:yrzysokhrnfqrhw4oayevpjyn4