An Improved Learning Algorithm Based on The Broyden-Fletcher-Goldfarb-Shanno (BFGS) Method For Back Propagation Neural Networks

Nawi, Nazri Mohd; Ransing, Meghana R.; Ransing, R. S.

doi:10.1109/isda.2006.95

Cited by 51 publications

(38 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This algorithm depends upon several parameters such as a number of hidden nodes at the hidden layers 'learning rate, momentum rate, activation function and the number of training to take place. Furthermore, these parameters could change the performance on the learning from bad to good accuracy [23].…”

Section: Neural Networkmentioning

confidence: 99%

Data Mining and Neural Networks: The Impact of Data Representation

Siraj¹,

Omer²,

Hasan³

2012

Advances in Data Mining Knowledge Discovery and Applications

View full text Add to dashboard Cite

Section: Neural Networkmentioning

confidence: 99%

Data Mining and Neural Networks: The Impact of Data Representation

Siraj¹,

Omer²,

Hasan³

2012

Advances in Data Mining Knowledge Discovery and Applications

View full text Add to dashboard Cite

“…First, a novel approach for improving the training efficiency of gradient descent method (BP algorithm) which was presented by Nawi et al [12] are discussed. Their method modified the initial search direction by changing the gain value adaptively for each node.…”

Section: Methodsmentioning

confidence: 99%

“…Algorithm [12] : Initialize the weight vector with random values and the vector of gain values with one. Repeat the following steps 1, 2 and 3 on an epoch-by-epoch basis until the given error minimization criteria are satisfied.…”

Section: Methodsmentioning

confidence: 99%

A Modified Conjugate Gradient Formula for Back Propagation Neural Network Algorithm

Al-Bayati¹,

Sulaiman²,

Sadiq³

2009

J. of Computer Science

View full text Add to dashboard Cite

Problem statement:The Conjugate Gradient (CG) algorithm which usually used for solving nonlinear functions is presented and is combined with the modified Back Propagation (BP) algorithm yielding a new fast training multilayer algorithm. Approach: This study consisted of determination of new search directions by exploiting the information calculated by gradient descent as well as the previous search direction. The proposed algorithm improved the training efficiency of BP algorithm by adaptively modifying the initial search direction. Results: Performance of the proposed algorithm was demonstrated by comparing it with the Neural Network (NN) algorithm for the chosen test functions. Conclusion: The numerical results showed that number of iterations required by the proposed algorithm to converge was less than the both standard CG and NN algorithms. The proposed algorithm improved the training efficiency of BP-NN algorithms by adaptively modifying the initial search direction.

show abstract

“…The error back propagation training was provided by Broyden-Fletcher-Goldfarb-Shanno (BFGS) training algorithm which is well suited for the unconstrained nonlinear multi-dimensional problems [25]. This algorithm provided a fast and efficient back propagation neural network training by adaptively modifying the initial search direction to improve the training efficiency [26].…”

Section: Artificial Neural Network Modelingmentioning

confidence: 99%

Intelligent Multivariate Model for the Optical Detection of Total Organic Carbon

Kokya

Mehrdadi

Ardestani

et al. 2016

J. Chil. Chem. Soc.

View full text Add to dashboard Cite

UV inactivity and fluorescence irradiance of various organic substances are the major drawbacks for a wide applicability of UV based TOC assessment models, especially in drinking water utilities and environmental fields. The adoption of an intelligent model is the key factor to access a reliable and effective detection. The accurate training of the artificial neural network model and backward elimination of less significant parameters, conferred more predictive properties to TOC detection. This led to an efficient optimal TOC detection model based on turbidity, UV 254 absorbance and true color. The validation of model performance was investigated through application of untrained scenarios. The outcome of the validation analysis showed a correlation coefficient of 0.87 and root mean square error of 0.48 while the training performance of the model showed 0.95 and 0.33 respectively. The results indicated that the trained ANN model was efficiently capable for TOC detection in water resources based on the main drivers.

show abstract

An Improved Learning Algorithm Based on The Broyden-Fletcher-Goldfarb-Shanno (BFGS) Method For Back Propagation Neural Networks

Cited by 51 publications

References 16 publications

Data Mining and Neural Networks: The Impact of Data Representation

Data Mining and Neural Networks: The Impact of Data Representation

A Modified Conjugate Gradient Formula for Back Propagation Neural Network Algorithm

Intelligent Multivariate Model for the Optical Detection of Total Organic Carbon

Contact Info

Product

Resources

About