In this paper we proposed a new method for isolated handwritten Farsi/Arabic characters and numerals recognition using fractal codes. Fractal codes represent affine transformations which when iteratively applied to the range-domain pairs in an arbitrary initial image, the result is close to the given image. Each fractal code consists of six parameters such as corresponding domain coordinates fo...

This paper presents results of analysis of few kinds of network traffic using Holt-Winters methods and Multilayer Perceptron. It also presents Anomaly Detection – a Snort-based network traffic monitoring tool which implements a few models of traffic prediction. Povzetek: Predstavljena je metoda za modeliranje in iskanje anomalij v omrežju.

Robot recognition is a very important point for further improvements in game-play in RoboCup middle size league. In this paper we present a neural recognition method we developed to find robots using different visual information. Two algorithms are introduced to detect possible robot areas in an image and a subsequent recognition method with two combined multi-layer perceptrons is used to class...

A multilayer perceptron classifier is then used to automatically detect the normal from the pathologia files. Results are compared with those obtained for the original database, using confusion matrices and DET plots. There are no significant differences between the designed detectors

In recent years, many attempts have been made to predict the behavior of bonds, currencies, stocks, or stock markets. In this paper, the StandardlkPoors 500 Index is modeled using different neural network classification architectures. Most previous experiments used multilayer perceptrons for stock market forecasting. In this paper, a multilayer perceptron architecture and ZL probabilistic neura...

Selective attention learning is proposed to improve the speed of the error backpropagation algorithm for fast speaker adaptation. Class-selective relevance for measuring the importance of a hidden node in a multilayer Perceptron is employed to selectively update the weights of the network, thereby reducing the computational cost for learning. c © 2002 Elsevier Science B.V. All rights reserved.

One of the central issues in neural network research is how to find an optimal MultiLayer Perceptron architecture. The number of neurons, their organization in layers, as well as their connection scheme have a considerable influence on network learning, and on the capacity for generalization [7]. A solution to find out these parameters is needed: The neuro-evolution ([1,2,4,5]). The novelty is ...

Different kinds of Multilayer Perceptrons, using a back-propagation learning algonthm, have been used to perform data compression tasks. Depending upon the architecture and the type of problern learned to solve ( classification or auto-association), the networks provide different kinds of dimensionality reduction preserving different properties of the data space. Some experiments show that usmg...

A multi-layered perceptron type neural network is presented and analyzed in this paper. All neuronal parameters such as input, output, action potential and connection weight are encoded by quaternions, which are a class of hypercomplex number system. Local analytic condition is imposed on the activation function in updating neurons’ states in order to construct learning algorithm for this netwo...

This paper presents DMP3 (Dynamic Multilayer Perceptron 3), a multilayer perceptron (MLP) constructive training method that constructs MLPs by incrementally adding network elements of varying complexity to the network. DMP3 differs from other MLP construction techniques in several important ways, and the motivation for these differences are given. Information gain rather than error minimization...