Recurrent neural networks (RNNs) trained with gradient-based algorithms such as real-time recurrent learning or back-propagation through time have a drawback of slow convergence rate. These algorithms also need the derivative calculation through the error back-propagation process. In this paper, a derivative-free Kalman filter, so called the unscented Kalman filter (UKF), for training a fully c...

Sex identification in animals has biological importance. Humans are good at making this determination visually, but machines have not matched this ability. A neural network was trained to discriminate sex in human faces, and performed as well as humans on a set of 90 exemplars. Images sampled at 30x30 were compressed using a 900x40x900 fully-connected back-propagation network; activities of hid...

This paper, presents a theoretical and practical basis of preprocessing on handwritten text for character recognition using forward-feed neural networks. Afterwards, the Feed forward algorithm gives working of a neural network followed by the Back Propagation Algorithm which compromises Training, Calculating Error, and Modifying Weights. The proposed solutions focus on applying Back Propagation...

Currently, the back-propagation is the most widely applied neural network algorithm at present. However, its slow learning speed and local minima problem are often cited as the major weakness of the algorithm. In this paper, described are an adaptive training algorithm based on selective retraining of patterns through error analysis, and dynamic adaptation of learning rate and momentum through ...

In this paper, we adapt the classical learning algorithm for feed-forward neural networks when monotonicity is require in the input-output mapping. Such requirements arise, for instance, when prior knowledge of the process being observed is available. Monotonicity can be imposed by the addition of suitable penalization terms to the error function. The objective function, however, depends nonlin...

Method for visualization of learning processes for back propagation neural network is proposed. The proposed method allows monitor spatial correlations among the nodes as an image and also check a convergence status. The proposed method is attempted to monitor the correlation and check the status for spatially correlated satellite imagery data of AVHRR derived sea surface temperature data. It i...

This paper is proposed the face recognition method using PCA with neural network back error propagation learning algorithm .In this paper a feature is extracted using principal component analysis and then classification by creation of back propagation neural network. We run our algorithm for face recognition application using principal component analysis, neural network and also calculate its p...

Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically, feed-forward artificial neural networks are trained with three different back propagation algorithms, ...

Many connectionist learning models are implemented using a gradient descent in a least squares error function of the output and teacher signal. The present model Fneralizes. in particular. back-propagation [1] by using Minkowski-r power metrics. For small r's a "city-block" error metric is approximated and for large r's the "maximum" or "supremum" metric is approached. while for r=2 the standar...

In this paper a new Back-propagation algorithm appropriately studied for modelling air pollution time series is proposed. The underlying idea is that of modifying the error definition in order to improve the capability of the model to forecast episodes of poor air quality. In the paper five different expressions of error definition are proposed and their performances are rigorously evaluated in...