A New Levenberg Marquardt based Back Propagation Algorithm Trained with Cuckoo Search

Nawi, Nazri Mohd; Khan, Abdullah; Rehman, Muhammad Zubair

doi:10.1016/j.protcy.2013.12.157

Cited by 82 publications

(26 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The back-propagation (BP) algorithm has recently emerged as one of the most efficient learning procedures for multi-layer networks, and it also is known as one of the most common algorithms used in the training of artificial neural networks [15]- [19]. The BP learning has become efficient with the establishment of its mathematical formula as the standard method or process in adjusting weights and biases for training an ANN in many domains [20]. The formulation of the back-propagation algorithm can be defined as follows:…”

Section: Methodsmentioning

confidence: 99%

The Effect of Pre-Processing Techniques and Optimal Parameters selection on Back Propagation Neural Networks

Nawi¹,

Hussein²,

Samsudin³

et al. 2017

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

Artificial Neural Network had gained a tremendous attention from researchers particularly because of the architecture of Artificial Neural Network that laid the foundation as a powerful technique in handling problems such as classification, pattern recognition, and data analysis. It is known for its data-driven, self-adaptive, and non-linear capabilities channel that is used in processing at high speed and the ability to learn the solution to a problem from a set of examples. Recently, research in Neural Network training has become a dynamic area of research, with the Multi-Layer Perceptron (MLP) trained with Back-Propagation (BP) was the most popular and been worked on by various researchers. In this study, the performance analysis based on BP training algorithms; gradient descent and gradient descent with momentum, both using the sigmoidal and hyperbolic tangent activation functions, coupled with pre-processing techniques are executed and compared. The Min-Max, Z-Score, and Decimal Scaling preprocessing techniques are analyzed. The simulations results generated from some selected benchmark datasets reveal that preprocessing the data greatly increase the ANN convergence, with Z-Score producing the overall best performance on all datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

The Effect of Pre-Processing Techniques and Optimal Parameters selection on Back Propagation Neural Networks

Nawi¹,

Hussein²,

Samsudin³

et al. 2017

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

show abstract

“…The proposed method had significantly improved the backpropagation training algorithm. The detail of the proposed algorithm by Nazri can be referred to some papers [12], [13], [14].…”

Section: Methodsmentioning

confidence: 99%

Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks

Nawi

Hamid

Samsudin

et al. 2017

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

The limitations of the existing Knowledge Hyper-surface method in learning cause and effect relationships in the manufacturing process is explored. A new approach to enhance the performance of the current Knowledge Hyper-surface method has been proposed by constructing midpoints between each primary weight along each dimension by using a quadratic Lagrange interpolation polynomial. The new secondary-weight values, generated due to the addition of midpoints, were also represented as a linear combination of the corresponding primary/axial weight values. An improved neural networks in learning from examples have also been proposed where both of the proposed algorithms able to constrain the shape of the surface in two-dimensional and multidimensional cases and produced more realistic and acceptable results as compared to the previous version. The ability of the proposed approach to models the exponential increase/decrease in the belief values by using high-ordered polynomials without introducing 'over-fitting' effects was investigated. The performance of the proposed method in modelling the exponential increase/decrease in belief values was carried out on real cases taken from real casting data. The computed graphical results of the proposed methods were compared with the current Knowledge Hyper-surface and neural-network methods. As a result, the proposed methods correctly predict the sensitivity of process-parameter variations with the occurrence of a defect and very important area of research in a robust design methodology.

show abstract

“…In the formula represented above, the ideal and best solutions or the nests that are selected portray the optimal solution (which denotes the weight space and the bias corresponding this in the optimization studies of the NN) compared to this problem and the amount of food source that is portrayed in this solution [8].…”

Section: Artificial Neural Network With Hybrid Genetic Algorithm and mentioning

confidence: 99%

An Artificial Neural Network Genetic Algorithm with Shuffled Frog Leap Algorithm for Software Defect Prediction

2019

IJITEE

View full text Add to dashboard Cite

Defect prediction performances are significant to attain quality of the software and to understand previous errors. In this work, for assessing the classification accuracy, precision, and recall and F measure for various classifiers are used. The artificial neural network optimizations make the assumption that more than two algorithms for one optimization have been implemented. The optimization makes use of a heuristic for choosing the best of the algorithms for being applied in a particular situation. An approach of hybrid optimization for designing of the linkages method and is used for the dimensional synthesis of the mechanism. The ANN models are assisted in their convergence towards a global minimum by the multi-directional search algorithm that is incorporated in the GA. The results have shown an accuracy of classification of the NN-hybrid shuffled from algorithm to perform better by about 5.94% than that of the fuzzy classifiers and by about 3.59% of the NN-Lm training and by about 1.42% of the NN-shuffled frog algorithm..

show abstract

A New Levenberg Marquardt based Back Propagation Algorithm Trained with Cuckoo Search

Cited by 82 publications

References 14 publications

The Effect of Pre-Processing Techniques and Optimal Parameters selection on Back Propagation Neural Networks

The Effect of Pre-Processing Techniques and Optimal Parameters selection on Back Propagation Neural Networks

Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks

An Artificial Neural Network Genetic Algorithm with Shuffled Frog Leap Algorithm for Software Defect Prediction

Contact Info

Product

Resources

About