This paper presentsa classofmodifiedHopfieldneuralnetworks and theiruse insolvingaircraftoptimalcontroland identificationproblems.This classofnetworksconsistsofparallelrecurrentnetworks which have variabledimensions that can bechanged tofithe problemsunder considezal;ion.Ithas a structureto implement aninversetransformationthatisessentialforembedding opti...

This paper introduces a gradient-based reward prediction update mechanism to the XCS classifier system as applied in neuralnetwork type learning and function approximation mechanisms. A strong relation of XCS to tabular reinforcement learning and more importantly to neural-based reinforcement learning techniques is drawn. The resulting gradient-based XCS system learns more stable and reliable i...

The aim of this work is to present a library, developed in Modelica, which provides the neural network mathematical model. This library is developed to be used to simulate a non-linear system, previously identified through a specific neural network training system. The NeuralNetwork library is developed in Modelica 2.2 and it offers all the required capabilities to create and use different kind...

In this study we address the problem of training a neuralnetwork for language identification using both labeled and unlabeled speech samples in the form of i-vectors. We propose a neural network architecture that can also handle out-of-set languages. We utilize a modified version of the recently proposed Ladder Network semisupervised training procedure that optimizes the reconstruction costs of...

The damage identification problem in mechanical structures is a process of determining parameters based on numerical analysis from a comparison on measurement data and the output data from a mathematical model. It is an important research topic. The main idea behind the damage identification problem, using displacement data, is that the structural damage will manifest a changing in the displace...

The paper deals with the problem of a robust fault diagnosis for Linear Parameter-Varying (LPV) systems with Recurrent NeuralNetwork (RNN). The preliminary part of the paper describes the derivation of a discrete-time polytopic LPV model with RNN. Subsequently, a robust fault detection, isolation and identification scheme is developed, which is based on the observer and H∞ framework for a class...

In this paper, a variant of Backpropagation algorithm is proposed for feed-forward neural networks learning. The proposed algorithm improve the backpropagation training in terms of quick convergence of the solution depending on the slope of the error graph and increase the speed of convergence of the system. Simulations are conducted to compare and evaluate the convergence behavior and the spee...

This paper focuses on comparing between using Support Vector Machine based ranking (SVMRank) and Bidirectional LongShort-Term-Memory (bi-LSTM) neuralnetwork based sequence labeling in building a state-of-the-art Arabic part-ofspeech tagging system. Using SVMRank leads to state-of-the-art results, but with a fair amount of feature engineering. Using bi-LSTM, particularly when combined with word ...

In this paper, we present a state-space formulation of a neuralnetwork-based hidden dynamic model of speech whose parameters are trained using an approximate EM algorithm. The training makes use of the results of an off-the-shelf formant tracker (during the vowel segments) to simplify the complex sufficient statistics that would be required in the exact EM algorithm. The trained model, consisti...

This paper addresses the use of neural networks as a metamodelling technique for discrete event stochastic simulation to reduce signi"cantly the computational burden involved by the simulations. A sophisticated computer model has been developed to anticipate the propagation of the green alga Caulerpa taxifolia in the northwestern Mediterranean sea. The simulation model provides reliable predict...