Kalman filter based training algorithms for recurrent neural networks provide a clever alternative to the standard backpropagation in time. However, these algorithms do not take into account the optimization of the hidden state variables of the recurrent network. In addition, their formulation requires Jacobian evaluations over the entire network, adding to their computational complexity. In th...

An empirical study of methods of handling missing values in a backpropagation neural network is presented. Neural networks can be applied to many real world systems to perform classification, pattern recognition or prediction on the basis of input data. However, many such applications cannot guarantee that the data provided to the network will be complete. The backpropagation network does not l...

Learning process is essential for good performance when a neural network is applied to a practical application. The backpropagation algorithm [1] is a well-known learning method widely used in most neural networks. However, since the backpropagation algorithm is time-consuming, much research have been done to speed up the process. The block backpropagation algorithm, which seems to be more effi...

Backpropagation (BP) adalah sebuah metode yang digunakan dalam training Neural Network (NN) untuk menentukan parameter bobot yang sesuai. Proses penentuan parameter bobot dengan menggunakan metode backpropagation sangat dipengaruhi oleh pemilihan nilai learning rate (LR)-nya. Penggunaan nilai learning rate yang kurang optimal berdampak pada waktu komputasi yang lama atau akurasi klasifikasi yan...

In this paper a topology of neural network intrusion detection system is proposed on which different backpropagation algorithms are benchmarked. The proposed methodology uses sampled data from KddCup99 data set, an intrusion detection attacks database that is a standard for the evaluation of intrusion detection systems. The performance of backpropagation algorithms implemented in batch mode, is...

This paper explores the application of artificial neural networks for online identification of a multimachine power system. A recurrent neural network has been proposed as the identifier of the two area, four machine system which is a benchmark system for studying electromechanical oscillations in multimachine power systems. This neural identifier is trained using the static Backpropagation alg...

Context-aware systems have received greater interest in the computing community. In order to provide relevant services at context-aware applications, the first task is to locate the user, what can be done preferably dynamically and intelligently. However, indoor mobile users localization is not a trivial problem, since it involves checking various devices, transmitting signals simultaneously on...

This paper presents experimental results of an original approach to the Neural Network learning architecture for the control and the adaptive control of mobile robots. The basic idea is to use non-recurrent multi-layer-network and the backpropagation algorithm without desired outputs, but with a quadratic criterion which spezify the control objective. To illustrate this method, we consider an e...