In this work an approach for time series forecasting by simulating stochastic processes through time lagged feed-forward neural network is presented. The learning rule used to adjust the neural network (NN) weights is based on the Levenberg-Marquardt method. In function of the long or short term stochastic dependence of the time series, an on-line heuristic law to set the training process and t...

Arti3cial neural networks (ANNs) have recently gained attention as fast and 5exible vehicles to microwave modeling, simulation, and optimization. In this study, ANNs, based on the multilayer perceptron, were presented for accurate computation of the quasistatic parameters of asymmetric coplanar waveguides (ACPWs). Multilayer perceptron neural networks (MLPNNs) were trained with backpropagation,...

Brain-Computer Interfaces (BCIs) measure brain signals activity, intentionally and unintentionally induced by users, and provides a communication channel without depending on the brain’s normal peripheral nerves and muscles output pathway. Feature Selection (FS) is a global optimization machine learning problem that reduces features, removes irrelevant and noisy data resulting in acceptable rec...

The aim of this paper is to propose a new Kalman Filter Recurrent Neural Network (KFRNN) topology and a recursive Levenberg-Marquardt (L-M) algorithm of its learning capable to estimate states and parameters of a highly nonlinear Continuous Stirred Tank Bioreactor (CSTR) in noisy environment. The estimated parameters and states obtained by the proposed KFRNN identifier are used to design an ind...

We present regularization tools for training small, medium and large feed-forward artiicial neural networks. The determination of the weights leads to very ill-conditioned nonlinear least squares problems and regularization is often suggested to get control over the network complexity, small variance error, and to get a nice optimization problem. The algorithms proposed explicitly use a sequenc...

In this work, a recursive Levenberg-Marquardt (LM) learning algorithm in the complex domain is developed and applied to the learning of an adaptive control scheme composed by ComplexValued Recurrent Neural Networks (CVRNN). We simplified the derivation of the LM learning algorithm using a diagrammatic method to derive the adjoint CVRNN used to obtain the gradient terms. Furthermore, we apply th...

ISSN 2277-5064 | © 2013 Bonfring Abstract--This paper presents a neural network based on Levenberg-Marquardt back-propagation algorithm for prediction of degree of angiographic coronary heart disease. The novelty of this work is training a one hidden layer neural network with Levenberg-Marquardt back-propagation algorithm for multivariate large dataset. An ANN model is developed for prediction ...

The objective of this paper is to present and make a comparative study of several inverse kinematics methods for serial manipulators, based on the Jacobian matrix. Besides the well-known Jacobian transpose and Jacobian pseudo-inverse methods, three others, borrowed from numerical analysis, are presented. Among them, two approximation methods avoid the explicit manipulability matrix inversion, w...

We compare the two well-known global optimization methods, simulated annealing and genetic optimization, to a local gradient-based optimization technique. We rate the applicability of each method in terms of the minimal achievable target value for a given number of simulation runs in an inverse modeling application. The gradient-based optimizer used in the experiment is based on the Levenberg-M...

This paper investigates artificial neural networks prediction modeling of foreign currency rates using Levenberg Marquardt (LM) learning algorithms. The models were trained from historical data using US Dollar (USD) currency rates against Indonesian Rupiah (IDR). The forecasting performance of the models was evaluated using a number of statistical measurements and compared. The results show tha...