In this paper, a new adjustment to the damping parameter of the Levenberg-Marquardt algorithm is proposed to save training time and to reduce error oscillations. The damping parameter of the Levenberg-Marquardt algorithm switches between a gradient descent method and the Gauss-Newton method. It also affects training speed and induces error oscillations when a decay rate is fixed. Therefore, our...

Back propagation neural network (BPNN) algorithm is a widely used technique in training artificial neural networks. It is also a very popular optimization procedure applied to find optimal weights in a training process. However, traditional back propagation optimized with Levenberg marquardt training algorithm has some drawbacks such as getting stuck in local minima, and network stagnancy. This...

According to the structure of the BP neural network and the algorithm, choose three methods of BP neural network algorithm was improved, through analysis and comparison, computing speed is faster, more accurate judgment Levenberg Marquardt algorithm as the improved algorithm of optimal; Using the algorithm to the established BP neural network for training analysis; Then use the Matlab software,...

The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either...

Financial forecasting is an example of signal processing problems. A number of ways to train/learn the network are available. We have used Levenberg-Marquardt algorithm for error back-propagation for weight adjustment. Pre-processing of data has reduced much of the variation at large scale to small scale, reducing the variation of training data. Keywords— Gradient descent method, jacobian matri...

The objective of this study is to compare the predictive ability of Bayesian regularization with Levenberg–Marquardt Artificial Neural Networks. To examine the best architecture of neural networks, the model was tested with one-, two-, three-, four-, and five-neuron architectures, respectively. MATLAB (2011a) was used for analyzing the Bayesian regularization and Levenberg–Marquardt learning al...

For managing data in a smart card’s limited memory, containing medical and biometric images, images compression is resorted to. For image retrieval, it is necessary that the classification algorithm be efficient to search and locate the image in a compressed domain. This study proposes a novel training algorithm for Multi-Layer Perceptron Neural Network (MLP-NN) to classify compressed images. M...

Financial forecasting is an example of signal processing problems. A number of ways to train/learn the network are available. We have used Levenberg-Marquardt algorithm for error back-propagation for weight adjustment. Pre-processing of data has reduced much of the variation at large scale to small scale, reducing the variation of training data. Keywords— Gradient descent method, jacobian matri...

In our previous work we proposed some extensions of the Levenberg-Marquardt algorithm; the Bacterial Memetic Algorithm and the Bacterial Memetic Algorithm with Modified Operator Execution Order for fuzzy rule base extraction from inputoutput data. Furthermore, we have investigated fuzzy flip-flop based feedforward neural networks. In this paper we introduce the adaptation of the Bacterial Memet...

This paper investigates the use of three back-propagation training algorithms, Levenberg-Marquardt, conjugate gradient and resilient back-propagation, for the two case studies, stream-flow forecasting and determination of lateral stress in cohesionless soils. Several neural network (NN) algorithms have been reported in the literature. They include various representations and architectures and t...