Learn More
In this letter, a new approach for the learning process of multilayer feedforward neural network is introduced. This approach minimizes a modified form of the criterion used in the standard backpropagation algorithm. This criterion is based on the sum of the linear and the nonlinear quadratic errors of the output neuron. The quadratic linear error signal is(More)
In this paper we have proposed a new defect detection algorithm based on local homogeneity and hotteling model to localize defects in various textures images. Firstly, the local homogeneity of each pixel is computed to construct a new homogeneity image denoted as (h-image). Then a wavelet transform, in order to extract features details, is applied. After,(More)
In this paper, the Davidon Fletcher Powell (DFP) algorithm for nonlinear least squares is proposed to train multilayer perceptron (MLP). Applied on both a single output layer perceptron and MLP, we find that this algorithm is faster than the Marquardt-Levenberg (ML) algorithm known as the fastest algorithm used to train MLP until now. The number of(More)
In this work a new method for image edge detection based on multilayer perceptron (MLP) is proposed. The method is based on updating a MLP to learn a set of contours drawn on a 3×3 grid and then take advantage of the network generalization capacity to detect different edge details even for very noisy images. The method is applied first to Gray scale(More)
In this work a new approach for the learning process of multilayer perceptron Neural Networks (NN) is proposed. This approach minimizes a modified form of the criterion used in the standard back-propagation algorithm (SBP) formed by the sum of the linear and the nonlinear quadratic errors of the neuron. To determine the desired target in the hidden layers(More)
In this paper, a new approach to quadratic blind system identification is proposed. This approach enables a nonlinear relationship between model kernels and output cumulants up to the third order by means of Genetic Algorithm (GA). Simulation results are presented to show good performance of this approach.
The blind identification of a special class of nonlinear system is pursued in this paper. In particular a genetic algorithm is developed for blind identification of quadratic Volterra model excited by an unobservable input signal which can either be a stationary Gaussian process or an i.i.d process. This approach enables a nonlinear relationship between(More)
  • S. Abid, – M. Chtourou, – M. Djemel
  • 2013
Article history: Received: 26.11.2012. Received in revised form: 25.02.2013. Accepted: 25.02.2013. Training and topology design of artificial neural networks are important issues with large application. This paper deals with an improved algorithm for feed forward neural networks (FNN)s training. The association of an incremental approach and the Lyapunov(More)