In this work we discuss the design of a novel non-linear mapping method for visual classification based on multilayer perceptrons (MLP) and assigned class target values. In training the perceptron, one or more target output values for each class in a 2-dimensional space are used. In other words, class membership information is interpreted visually as closeness to target values in a 2D feature s...

Multilayer perceptron (MLP), normally trained by the offline backpropagation algorithm, could not adapt to the changing air quality system and subsequently underperforms. To improve this, the extended Kalman filter is adopted into the learning algorithm to build a time-varying multilayer perceptron (TVMLP) in this study. Application of the TVMLP to model the daily averaged concentration of the ...

Neural Networks (NNs) are capable of learning high complex, nonlinear input-output mappings. This characteristic of NNs enables them to be used in nonlinear system modeling and prediction applications. On the other hand, the wavelet decomposition provides a powerful tool for functional approximation. In this paper, a kind of Wavelet Neural Networks (WNNs) is proposed for Differential GPS (DGPS)...

The Particle Swarm Optimization (PSO) was used to select the three best inputs to explain the input-output relationship of both 'defects' and 'time' models. A ranking-based system was used to select the best features. Using this system, the value of each particle in the swarm represents the importance of each feature. During optimization, the three best-ranked features were used to train the Mu...

In the last few years a lot of research has been carried out in the field of deliverance of information for improving its efficiency and reliability. However, the systematic analysis and verification of channel performance triggered wide interest of new researchers. The popular technique for transmission of signals over wireless channels was orthogonal frequency division multiplexing (OFDM). In...

Consider a multilayer perceptron (MLP) with d inputs, a single hidden sigmoidal layer and a linear output. By adding an additional d inputs to the network with values set to the square of the rst d inputs, properties reminiscent of higher-order neural networks and radial basis function networks (RBFN) are added to the architecture with little added expense in terms of weight requirements. Of pa...

In this paper, we described and developed a framework for Multilayer Perceptron (MLP) to work on low level image processing, where MLP will be used to perform image super-resolution. Meanwhile, MLP are trained with different types of images from various categories, hence analyse the behaviour and performance of the neural network. The tests are carried out using qualitative test, in which Mean ...

The discrimination powers of Multilayer perceptron (MLP) and Learning Vector Quantisation (LVQ) networks are compared for overlapping Gaussian distributions. It is shown, both analytically and with Monte Carlo studies, that the MLP network handles high dimensional problems in a more eecient way than LVQ. This is mainly due to the sigmoidal form of the MLP transfer function, but also to the the ...

This paper presents a method of recognition of isolated offline handwritten Devanagari numerals using wavelets and neural network classifier. This method of optical character recognition takes the handwritten numeral image as input. After pre-processing, it is subjected to single level wavelet decomposition using Daubechies-4 wavelet filter. This wavelet decomposition allows viewing the input n...

Several neural network architectures have been developed over the past several years. One of the most popular and most powerful architectures is the multilayer perceptron. This architecture will be described in detail and recent advances in training of the multilayer perceptron will be presented. Multilayer perceptrons are trained using various techniques. For years the most used training metho...