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...

BP Neural Network has a longer training time and a slow convergence. To deal with the defects of BP Neural Network a modified BP algorithm is proposed in the paper. The algorithm is applied for the control of Inverted Pendulum, a highly non linear system inherently being open loop unstable. Levenberg-Marquardt algorithm is used for the training purpose. The training samples are being collected ...

Efficient second order algorithm for training feedforward neural networks is presented. The algorithm has a similar convergence rate as the Lavenberg-Marquardt (LM) method and it is less computationally intensive and requires less memory. This is especially important for large neural networks where the LM algorithm becomes impractical. Algorithm was verified with several examples.

In this paper, we propose the block-diagonal matrix to approximate the Hessian matrix in the Levenberg Mar-quardt method in the training of neural networks. Two weight updating strategies, namely asynchronous and synchronous updating methods were investigated. Asyn-chronous method updates weights of one block at a time while synchronous method updates all weights at the same time. Variations of...

In this paper back-propagation artificial neural network (BPANN) with Levenberg–Marquardt algorithm is employed to predict the limiting drawing ratio (LDR) of the deep drawing process. To prepare a training set for BPANN, some finite element simulations were carried out. die and punch radius, die arc radius, friction coefficient, thickness, yield strength of sheet and strain hardening exponent ...

RNNs have local feedback loops within the network which allows them to shop earlier accessible patterns. This network can be educated with gradient descent back propagation and optimization technique such as second-order methods; conjugate gradient, quasi-Newton, Levenberg-Marquardt have also been used for networks training [14, 15]. But still this algorithm is not definite to find the global m...

Abstract This paper presents a parallel approach to the Levenberg-Marquardt algorithm (LM). The use of train neural networks is associated with significant computational complexity, and thus computation time. As result, when network has big number weights, becomes practically ineffective. article new computations in learning algorithm. proposed solution based on vector instructions effectively ...

In this work, we describe a method for the classification of respiratory states based on four significant features using Artificial neural network (ANN). These features are extracted from the respiratory signals using modified threshold algorithm were fed as input parameters to the ANN for classification. A gradient based search algorithms are usually being used in ANN to find a set of suitable...

This paper presents a novel training algorithm for fuzzy inference systems. The algorithm combines the Levenberg-Marquardt algorithm with variable structure systems approach. The combination is performed by expressing the parameter update rule in continuous time and application of sliding mode control method to the gradient based training procedure. The proposed combination therefore exhibits a...

The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial Neural Networks but its computational complexity and the difficulty to compute the trust region have made it very difficult to develop a true iterative version to use in on-line training. The algorithm is frequently used for off-line training in batch versions although some attempts have been made ...