Function approximation is an instance of supervised learning which is one of the most studied topics in machine learning, artificial neural networks, pattern recognition, and statistical curve fitting. In principle, any of the methods studied in these fields can be used in reinforcement learning. Multi-layered feed-forward neural networks (MLFNN) have been extensively used for the purpose of fu...

The application of artificial neural networks (ANNs) for prognostic and diagnostic classification in clinical medicine has become very popular. In particular, feed-forward neural networks have been used extensively, often accompanied by exaggerated statements of their potential. In this paper, the essentials of feed-forward neural networks and their statistical counterparts (that is, logistic r...

The intrinsic hysteresis behavior of piezoelectric material limits the tracking control accuracy of the actuators. This paper describes a tracking control method for piezoelectric actuators based on the combination of feedforward and feedback loops. The hysteresis of piezoelectric actuators is linearized in feedforward loop with an inverse hysteresis model based on a neural network. The number ...

Utilization of membrane humidifiers is one of the methods commonly used to humidify reactant gases in polymer electrolyte membrane fuel cells (PEMFC). In this study, polymeric porous membranes with different compositions were prepared to be used in a membrane humidifier module and were employed in a humidification test. Three different neural network models were developed to investigate several...

This paper presents novel coaxial probe feed, microstrip antenna with dual bandwidth design using a soft computing tool Artificial Neural Network. By varying the position of the feed, dual bandwidths of 8.08% and 8.15% is achieved which is further simulated on ANN tool. The antenna is fed by coaxial probe feeding technique. The obtained bandwidth from the IE3D is used a training set to train th...

RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...

Incremental artificial neural networks grow when they learn and shrink when they forget. Competitive Hebbian learning generates the network structure by addition and removal of cells and links. Thus, no network design phase is necessary. The growing cell structure and the growing neural gas network may replace common feed-forward networks in a lot of classification and interpolation tasks.

Early detection of cancer is the most promising way to enhance a patient's chance for survival. This paper presents a computer aided classification method in computed tomography (CT) images of lungs developed using artificial neural network. The entire lung is segmented from the CT images and the parameters are calculated from the segmented image. The statistical parameters like mean, standard ...

An artificial neural network study of gas drying by adsorption in fixed bed of composite materials is presented in this paper. The experimental investigations were carried out at two values of relative humidity and three values of air flow rate respectively. The experimental data were employed in the design of the feed forward neural networks for modeling the evolution in time of some adsorptio...

The aim of this paper is to survey the feed-forward and self-organizing neural networks for the text document retrieval models, which retrieve text documents in a natural language. These models come from linguistic and conceptual approach of the text document analysis, where problems of document representation and document database creation are being solved. The proposed structure of the feed-f...