Optimal Unsupervised Learning in Feedforward Neural Networks

We investigate the properties of feedforward neural networks trained with Hebbian learning algorithms. A new unsupervised algorithm is proposed which produces statistically uncorrelated outputs. The algorithm causes the weights of the network to converge to the eigenvectors of the input correlation with largest eigenvalues. The algorithm is closely related to the technique of Self-supervised Backpropagation, as well as other algorithms for unsupervised learning. Applications of the algorithm to texture processing, image coding, and stereo depth edge detection are given. We show that the algorithm can lead to the development of filters qualitatively similar to those found in primate visual cortex.

Feedforward neural networks based on PPS-wavelet activation functions

Function approximation is a very important task in environments where computation has to be based on extracting information from data samples in real world processes. Neural networks and wavenets have been recently seen as attractive tools for developing efficient solutions for many real world problems in function approximation. In this paper, it is shown how feedforward neural networks can be built using a different type of activation function referred to as the PPS-wavelet. An algorithm is presented to generate a family of PPS-wavelets that can be used to efficiently construct feedforward networks for function approximation.

Incremental neural networks for function approximation

A new strategy for incremental building of multilayer feedforward neural networks is proposed in the context of approximation of functions from R-p to R-q using noisy data. A stopping criterion based on the properties of the noise is also proposed. Experimental results for both artificial and real data are performed and two alternatives of the proposed construction strategy are compared.

Learning in neural networks and stochastic approximation methods with averaging

The problem of adjusting the weights (learning) in multilayer feedforward neural networks (NN) is known to be of a high importance when utilizing NN techniques in various practical applications. The learning procedure is to be performed as fast as possible and in a simple computational fashion, the two requirements which are usually not satisfied practically by the methods developed so far. Moreover, the presence of random inaccuracies are usually not taken into account. In view of these three issues, an alternative stochastic approximation approach discussed in the paper, seems to be very promising.

Multidimensional polynomial powers of sigmoid (PPS) Wavelet neural networks

Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical backpropagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As an example of application for the method proposed, it is studied the exclusive-or (XOR) problem.

Electric power systems transient stability analysis by neural networks

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

A fast electric load forecasting using adaptive neural networks

This work presents a procedure for electric load forecasting based on adaptive multilayer feedforward neural networks trained by the Backpropagation algorithm. The neural network architecture is formulated by two parameters, the scaling and translation of the postsynaptic functions at each node, and the use of the gradient-descendent method for the adjustment in an iterative way. Besides, the neural network also uses an adaptive process based on fuzzy logic to adjust the network training rate. This methodology provides an efficient modification of the neural network that results in faster convergence and more precise results, in comparison to the conventional formulation Backpropagation algorithm. The adapting of the training rate is effectuated using the information of the global error and global error variation. After finishing the training, the neural network is capable to forecast the electric load of 24 hours ahead. To illustrate the proposed methodology it is used data from a Brazilian Electric Company. © 2003 IEEE.

Determination of resonant frequencies of triangular and rectangular microstrip antennas, using artificial neural networks

This paper presents models that can be used in the design of microstrip antennas for mobile communications. The antennas can be triangular or rectangular. The presented models are compared with deterministic and empirical models based on artificial neural networks (ANN) presented in the literature. The models are based on Perceptron Multilayer (PML) and Radial Basis Function (RBF) ANN. RBF based models presented the best results. Also, the models can be embedded in CAD systems, in order to design microstrip antennas for mobile communications.

Analyzing MSI rules for the USA extracted from a feedforward neural network

This paper introduces a mechanism for generating a series of rules that characterize the money price relationship for the USA, defined as the relationship between the rate of growth of the money supply and inflation. Monetary component data is used to train a selection of candidate feedforward neural networks. The selected network is mined for rules, expressed in human-readable and machine-executable form. The rule and network accuracy are compared, and expert commentary is made on the readability and reliability of the extracted rule set. The ultimate goal of this research is to produce rules that meaningfully and accurately describe inflation in terms of the monetary component dataset.

Optimization of the AZO dyes decoloration process through neural networks: Determination of the H2O2 addition critical point

The concentration of hydrogen peroxide is an important parameter in the azo dyes decoloration process through the utilization of advanced oxidizing processes, particularly by oxidizing via UV/H2O2. It is pointed out that, from a specific concentration, the hydrogen peroxide works as a hydroxyl radical self-consumer and thus a decrease of the system`s oxidizing power happens. The determination of the process critical point (maximum amount of hydrogen peroxide to be added) was performed through a ""thorough mapping"" or discretization of the target region, founded on the maximization of an objective function objective (constant of reaction kinetics of pseudo-first order). The discretization of the operational region occurred through a feedforward backpropagation neural model. The neural model obtained presented remarkable coefficient of correlation between real and predicted values for the absorbance variable, above 0.98. In the present work, the neural model had, as phenomenological basis the Acid Brown 75 dye decoloration process. The hydrogen peroxide addition critical point, represented by a value of mass relation (F) between the hydrogen peroxide mass and the dye mass, was established in the interval 50 < F < 60. (C) 2007 Elsevier B.V. All rights reserved.

On Recurrent and Deep Neural Networks

L'apprentissage profond est un domaine de recherche en forte croissance en apprentissage automatique qui est parvenu à des résultats impressionnants dans différentes tâches allant de la classification d'images à la parole, en passant par la modélisation du langage. Les réseaux de neurones récurrents, une sous-classe d'architecture profonde, s'avèrent particulièrement prometteurs. Les réseaux récurrents peuvent capter la structure temporelle dans les données. Ils ont potentiellement la capacité d'apprendre des corrélations entre des événements éloignés dans le temps et d'emmagasiner indéfiniment des informations dans leur mémoire interne. Dans ce travail, nous tentons d'abord de comprendre pourquoi la profondeur est utile. Similairement à d'autres travaux de la littérature, nos résultats démontrent que les modèles profonds peuvent être plus efficaces pour représenter certaines familles de fonctions comparativement aux modèles peu profonds. Contrairement à ces travaux, nous effectuons notre analyse théorique sur des réseaux profonds acycliques munis de fonctions d'activation linéaires par parties, puisque ce type de modèle est actuellement l'état de l'art dans différentes tâches de classification. La deuxième partie de cette thèse porte sur le processus d'apprentissage. Nous analysons quelques techniques d'optimisation proposées récemment, telles l'optimisation Hessian free, la descente de gradient naturel et la descente des sous-espaces de Krylov. Nous proposons le cadre théorique des méthodes à région de confiance généralisées et nous montrons que plusieurs de ces algorithmes développés récemment peuvent être vus dans cette perspective. Nous argumentons que certains membres de cette famille d'approches peuvent être mieux adaptés que d'autres à l'optimisation non convexe. La dernière partie de ce document se concentre sur les réseaux de neurones récurrents. Nous étudions d'abord le concept de mémoire et tentons de répondre aux questions suivantes: Les réseaux récurrents peuvent-ils démontrer une mémoire sans limite? Ce comportement peut-il être appris? Nous montrons que cela est possible si des indices sont fournis durant l'apprentissage. Ensuite, nous explorons deux problèmes spécifiques à l'entraînement des réseaux récurrents, à savoir la dissipation et l'explosion du gradient. Notre analyse se termine par une solution au problème d'explosion du gradient qui implique de borner la norme du gradient. Nous proposons également un terme de régularisation conçu spécifiquement pour réduire le problème de dissipation du gradient. Sur un ensemble de données synthétique, nous montrons empiriquement que ces mécanismes peuvent permettre aux réseaux récurrents d'apprendre de façon autonome à mémoriser des informations pour une période de temps indéfinie. Finalement, nous explorons la notion de profondeur dans les réseaux de neurones récurrents. Comparativement aux réseaux acycliques, la définition de profondeur dans les réseaux récurrents est souvent ambiguë. Nous proposons différentes façons d'ajouter de la profondeur dans les réseaux récurrents et nous évaluons empiriquement ces propositions.

Multiple PID mapping using neural networks in a MIMO steam generator system

A neural network was used to map three PID operating regions for a two-input two-output steam generator system. The network was used in stand alone feedforward operation to control the whole operating range of the process, after being trained from the PID controllers corresponding to each control region. The network inputs are the plant error signals, their integral, their derivative and a 4-error delay train.

Sensitivity analysis by neural networks applied to power systems transient stability

This work presents a procedure for transient stability analysis and preventive control of electric power systems, which is formulated by a multilayer feedforward neural network. The neural network training is realized by using the back-propagation algorithm with fuzzy controller and adaptation of the inclination and translation parameters of the nonlinear function. These procedures provide a faster convergence and more precise results, if compared to the traditional back-propagation algorithm. The adaptation of the training rate is effectuated by using the information of the global error and global error variation. After finishing the training, the neural network is capable of estimating the security margin and the sensitivity analysis. Considering this information, it is possible to develop a method for the realization of the security correction (preventive control) for levels considered appropriate to the system, based on generation reallocation and load shedding. An application for a multimachine power system is presented to illustrate the proposed methodology. (c) 2006 Elsevier B.V. All rights reserved.