Boundedness and convergence of batch back-propagation algorithm with penalty for feedforward neural networks

Zhang, Huisheng; Wu, Wei; Yao, Mingchen

doi:10.1016/j.neucom.2012.02.029

Cited by 50 publications

(22 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, neural networks have become a very useful tool in the modeling of complicated systems because they have an excellent ability learn and to generalize (interpolate) the complicated relationships between input and output variables. Also, the ANNs behave as model free estimators; that is, they can capture and model complex input-output relations without the help of a mathematical model [15]. In other words, training neural networks, for example, eliminates the need for explicit mathematical modeling or similar system analysis.…”

Section: Overview Of Neural Networkmentioning

confidence: 99%

Estimation of Acceleration Amplitude of Vehicle by Back Propagation Neural Networks

Heidari

Homaei

2013

Advances in Acoustics and Vibration

View full text Add to dashboard Cite

This paper investigates the variation of vertical vibrations of vehicles using a neural network (NN). The NN is a back propagation NN, which is employed to predict the amplitude of acceleration for different road conditions such as concrete, waved stone block paved, and country roads. In this paper, four supervised functions, namely, newff, newcf, newelm, and newfftd, have been used for modeling the vehicle vibrations. The networks have four inputs of velocity ( ), damping ratio ( ), natural frequency of vehicle shock absorber ( ), and road condition (R.C) as the independent variables and one output of acceleration amplitude (AA). Numerical data, employed for training the networks and capabilities of the models in predicting the vehicle vibrations, have been verified. Some training algorithms are used for creating the network. The results show that the Levenberg-Marquardt training algorithm and newelm function are better than other training algorithms and functions. This method is conceptually straightforward, and it is also applicable to other type vehicles for practical purposes.

show abstract

Section: Overview Of Neural Networkmentioning

confidence: 99%

Estimation of Acceleration Amplitude of Vehicle by Back Propagation Neural Networks

Heidari

Homaei

2013

Advances in Acoustics and Vibration

View full text Add to dashboard Cite

show abstract

“…The experimental results show that NBPNN gave a more accurate result than the BP algorithm. In [14] a specific penalty to obtain the proportion of the norm of the weight or to prove the boundedness of the weights in the network training process is presented. The learning rate is set by an equation to be a small constant or an adaptive series.…”

Section: Related Workmentioning

confidence: 99%

Dynamically-adaptive Weight in Batch Back Propagation Algorithm via Dynamic Training Rate for Speedup and Accuracy Training

Al_Duais¹,

Mohamad²

2017

JTIT

View full text Add to dashboard Cite

Abstract-The main problem of batch back propagation (BBP) algorithm is slow training and there are several parameters need to be adjusted manually, such as learning rate. In addition, the BBP algorithm suffers from saturation training. The objective of this study is to improve the speed up training of the BBP algorithm and to remove the saturation training. The training rate is the most significant parameter for increasing the efficiency of the BBP. In this study, a new dynamic training rate is created to speed the training of the BBP algorithm. The dynamic batch back propagation (DBBPLR) algorithm is presented, which trains with adynamic training rate. This technique was implemented with a sigmoid function. Several data sets were used as benchmarks for testing the effects of the created dynamic training rate that we created. All the experiments were performed on Matlab. From the experimental results, the DBBPLR algorithm provides superior performance in terms of training, faster training with higher accuracy compared to the BBP algorithm and existing works.Keywords-artificial neural network (ANN), batch back propagation algorithm, dynamic training rate, speed up training, accuracy training.

show abstract

“…The gradient algorithm is bounded and convergent naturally (Zhang et al, 2012). Because of the high nonlinearity of neural network, this optimal step size was difficult to find when we applied gradient method.…”

Section: Batch Back-propagation Algorithmmentioning

confidence: 99%

Modeling of a natural lipstick formulation using an artificial neural network

et al. 2015

View full text Add to dashboard Cite

An artificial neural network (ANN) was applied in conjunction with experimental data from mixture experimental design to predict the melting point of lipstick formulation. The experimental data were utilized for training and testing of the suggested model. By using performance of ANN, the optimum parameters were pitaya seed oil 25 w/w%, virgin coconut oil 37 w/w%, beeswax 17 w/w%, candelilla wax 2 w/w% and carnauba wax 2 w/w%. The relative standard error under these parameters is only 0.8772%. It was found that batch back propagation (BBP) as the optimal algorithm and topology with configuration of 5 inputs, 2 hidden and 1 output nodes; respectively with the most importance relative parameter is carnauba wax 24.5%.

show abstract

Boundedness and convergence of batch back-propagation algorithm with penalty for feedforward neural networks

Cited by 50 publications

References 18 publications

Estimation of Acceleration Amplitude of Vehicle by Back Propagation Neural Networks

Estimation of Acceleration Amplitude of Vehicle by Back Propagation Neural Networks

Dynamically-adaptive Weight in Batch Back Propagation Algorithm via Dynamic Training Rate for Speedup and Accuracy Training

Modeling of a natural lipstick formulation using an artificial neural network

Contact Info

Product

Resources

About