Applications of the Sufficiency Principle in Acceleration of Neural Networks Trainig

One of the problems in AI tasks solving by neurocomputing methods is a considerable training time. This problem especially appears when it is needed to reach high quality in forecast reliability or pattern recognition. Some formalised ways for increasing of networks’ training speed without loosing of precision are proposed here. The offered approaches are based on the Sufficiency Principle, which is formal representation of the aim of a concrete task and conditions (limitations) of their solving [1]. This is development of the concept that includes the formal aims’ description to the context of such AI tasks as classification, pattern recognition, estimation etc.

Study of the Application of Neural Networks in Internet Traffic Engineering

In this study, we showed various approachs implemented in Artificial Neural Networks for network resources management and Internet congestion control. Through a training process, Neural Networks can determine nonlinear relationships in a data set by associating the corresponding outputs to input patterns. Therefore, the application of these networks to Traffic Engineering can help achieve its general objective: “intelligent” agents or systems capable of adapting dataflow according to available resources. In this article, we analyze the opportunity and feasibility to apply Artificial Neural Networks to a number of tasks related to Traffic Engineering. In previous sections, we present the basics of each one of these disciplines, which are associated to Artificial Intelligence and Computer Networks respectively.

Classification of Data to Extract Knowledge from Neural Networks

A major drawback of artificial neural networks is their black-box character. Therefore, the rule extraction algorithm is becoming more and more important in explaining the extracted rules from the neural networks. In this paper, we use a method that can be used for symbolic knowledge extraction from neural networks, once they have been trained with desired function. The basis of this method is the weights of the neural network trained. This method allows knowledge extraction from neural networks with continuous inputs and output as well as rule extraction. An example of the application is showed. This example is based on the extraction of average load demand of a power plant.

The Usage of Neural Networks for the Medical Diagnosis

The problem of cancer diagnosis from multi-channel images using the neural networks is investigated. The goal of this work is to classify the different tissue types which are used to determine the cancer risk. The radial basis function networks and backpropagation neural networks are used for classification. The results of experiments are presented.

Artificial neural networks for surface roughness prediction when face milling Al 7075-T7351

In this work, different artificial neural networks (ANN) are developed for the prediction of surface roughness (R a) values in Al alloy 7075-T7351 after face milling machining process. The radial base (RBNN), feed forward (FFNN), and generalized regression (GRNN) networks were selected, and the data used for training these networks were derived from experiments conducted using a high-speed milling machine. The Taguchi design of experiment was applied to reduce the time and cost of the experiments. From this study, the performance of each ANN used in this research was measured with the mean square error percentage and it was observed that FFNN achieved the best results. Also the Pearson correlation coefficient was calculated to analyze the correlation between the five inputs (cutting speed, feed per tooth, axial depth of cut, chip°s width, and chip°s thickness) selected for the network with the selected output (surface roughness). Results showed a strong correlation between the chip thickness and the surface roughness followed by the cutting speed. © ASM International.

Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM

One major drawback of coherent optical orthogonal frequency-division multiplexing (CO-OFDM) that hitherto remains unsolved is its vulnerability to nonlinear fiber effects due to its high peak-to-average power ratio. Several digital signal processing techniques have been investigated for the compensation of fiber nonlinearities, e.g., digital back-propagation, nonlinear pre- and post-compensation and nonlinear equalizers (NLEs) based on the inverse Volterra-series transfer function (IVSTF). Alternatively, nonlinearities can be mitigated using nonlinear decision classifiers such as artificial neural networks (ANNs) based on a multilayer perceptron. In this paper, ANN-NLE is presented for a 16QAM CO-OFDM system. The capability of the proposed approach to compensate the fiber nonlinearities is numerically demonstrated for up to 100-Gb/s and over 1000km and compared to the benchmark IVSTF-NLE. Results show that in terms of Q-factor, for 100-Gb/s at 1000km of transmission, ANN-NLE outperforms linear equalization and IVSTF-NLE by 3.2dB and 1dB, respectively.

Neural Networks in Bankruptcy Prediction - A Comparative Study on the Basis of the First Hungarian Bankruptcy Model

The article attempts to answer the question whether or not the latest bankruptcy prediction techniques are more reliable than traditional mathematical–statistical ones in Hungary. Simulation experiments carried out on the database of the first Hungarian bankruptcy prediction model clearly prove that bankruptcy models built using artificial neural networks have higher classification accuracy than models created in the 1990s based on discriminant analysis and logistic regression analysis. The article presents the main results, analyses the reasons for the differences and presents constructive proposals concerning the further development of Hungarian bankruptcy prediction.

An investigation of location effect on trip production using artificial neural networks

As traffic congestion exuberates and new roadway construction is severely constrained because of limited availability of land, high cost of land acquisition, and communities' opposition to the building of major roads, new solutions have to be sought to either make roadway use more efficient or reduce travel demand. There is a general agreement that travel demand is affected by land use patterns. However, traditional aggregate four-step models, which are the prevailing modeling approach presently, assume that traffic condition will not affect people's decision on whether to make a trip or not when trip generation is estimated. Existing survey data indicate, however, that differences exist in trip rates for different geographic areas. The reasons for such differences have not been carefully studied, and the success of quantifying the influence of land use on travel demand beyond employment, households, and their characteristics has been limited to be useful to the traditional four-step models. There may be a number of reasons, such as that the representation of influence of land use on travel demand is aggregated and is not explicit and that land use variables such as density and mix and accessibility as measured by travel time and congestion have not been adequately considered. This research employs the artificial neural network technique to investigate the potential effects of land use and accessibility on trip productions. Sixty two variables that may potentially influence trip production are studied. These variables include demographic, socioeconomic, land use and accessibility variables. Different architectures of ANN models are tested. Sensitivity analysis of the models shows that land use does have an effect on trip production, so does traffic condition. The ANN models are compared with linear regression models and cross-classification models using the same data. The results show that ANN models are better than the linear regression models and cross-classification models in terms of RMSE. Future work may focus on finding a representation of traffic condition with existing network data and population data which might be available when the variables are needed to in prediction.

A research platform for artificial neural networks with applications in pediatric epilepsy

This dissertation established a state-of-the-art programming tool for designing and training artificial neural networks (ANNs) and showed its applicability to brain research. The developed tool, called NeuralStudio, allows users without programming skills to conduct studies based on ANNs in a powerful and very user friendly interface. A series of unique features has been implemented in NeuralStudio, such as ROC analysis, cross-validation, network averaging, topology optimization, and optimization of the activation function’s slopes. It also included a Support Vector Machines module for comparison purposes. Once the tool was fully developed, it was applied to two studies in brain research. In the first study, the goal was to create and train an ANN to detect epileptic seizures from subdural EEG. This analysis involved extracting features from the spectral power in the gamma frequencies. In the second application, a unique method was devised to link EEG recordings to epileptic and nonepileptic subjects. The contribution of this method consisted of developing a descriptor matrix that can be used to represent any EEG file regarding its duration and the number of electrodes. The first study showed that the inter-electrode mean of the spectral power in the gamma frequencies and its duration above a specific threshold performs better than the other frequencies in seizure detection, exhibiting an accuracy of 95.90%, a sensitivity of 92.59%, and a specificity of 96.84%. The second study yielded that Hjorth’s parameter activity is sufficient to accurately relate EEG to epileptic and non-epileptic subjects. After testing, accuracy, sensitivity and specificity of the classifier were all above 0.9667. Statistical tests measured the superiority of activity at over 99.99 % certainty. It was demonstrated that (1) the spectral power in the gamma frequencies is highly effective in locating seizures from EEG and (2) activity can be used to link EEG recordings to epileptic and non-epileptic subjects. These two studies required high computational load and could be addressed thanks to NeuralStudio. From a medical perspective, both methods proved the merits of NeuralStudio in brain research applications. For its outstanding features, NeuralStudio has been recently awarded a patent (US patent No. 7502763).

Gesture Recognition Using Neural Networks Based on HW/SW Cosimulation Platform

Hardware/software (HW/SW) cosimulation integrates software simulation and hardware simulation simultaneously. Usually, HW/SW co-simulation platform is used to ease debugging and verification for very large-scale integration (VLSI) design. To accelerate the computation of the gesture recognition technique, an HW/SW implementation using field programmable gate array (FPGA) technology is presented in this paper. The major contributions of this work are: (1) a novel design of memory controller in the Verilog Hardware Description Language (Verilog HDL) to reduce memory consumption and load on the processor. (2) The testing part of the neural network algorithm is being hardwired to improve the speed and performance. The American Sign Language gesture recognition is chosen to verify the performance of the approach. Several experiments were carried out on four databases of the gestures (alphabet signs A to Z). (3) The major benefit of this design is that it takes only few milliseconds to recognize the hand gesture which makes it computationally more efficient.

A Research Platform for Artificial Neural Networks with Applications in Pediatric Epilepsy

This dissertation established a state-of-the-art programming tool for designing and training artificial neural networks (ANNs) and showed its applicability to brain research. The developed tool, called NeuralStudio, allows users without programming skills to conduct studies based on ANNs in a powerful and very user friendly interface. A series of unique features has been implemented in NeuralStudio, such as ROC analysis, cross-validation, network averaging, topology optimization, and optimization of the activation function’s slopes. It also included a Support Vector Machines module for comparison purposes. Once the tool was fully developed, it was applied to two studies in brain research. In the first study, the goal was to create and train an ANN to detect epileptic seizures from subdural EEG. This analysis involved extracting features from the spectral power in the gamma frequencies. In the second application, a unique method was devised to link EEG recordings to epileptic and non-epileptic subjects. The contribution of this method consisted of developing a descriptor matrix that can be used to represent any EEG file regarding its duration and the number of electrodes. The first study showed that the inter-electrode mean of the spectral power in the gamma frequencies and its duration above a specific threshold performs better than the other frequencies in seizure detection, exhibiting an accuracy of 95.90%, a sensitivity of 92.59%, and a specificity of 96.84%. The second study yielded that Hjorth’s parameter activity is sufficient to accurately relate EEG to epileptic and non-epileptic subjects. After testing, accuracy, sensitivity and specificity of the classifier were all above 0.9667. Statistical tests measured the superiority of activity at over 99.99 % certainty. It was demonstrated that 1) the spectral power in the gamma frequencies is highly effective in locating seizures from EEG and 2) activity can be used to link EEG recordings to epileptic and non-epileptic subjects. These two studies required high computational load and could be addressed thanks to NeuralStudio. From a medical perspective, both methods proved the merits of NeuralStudio in brain research applications. For its outstanding features, NeuralStudio has been recently awarded a patent (US patent No. 7502763).

Cascade artificial neural networks technique for solving ellipsometry problems

Ellipsometry is a well known optical technique used for the characterization of reflective surfaces in study and films between two media. It is based on measuring the change in the state of polarization that occurs as a beam of polarized light is reflected from or transmitted through the film. Measuring this change can be used to calculate parameters of a single layer film such as the thickness and the refractive index. However, extracting these parameters of interest requires significant numerical processing due to the noninvertible equations. Typically, this is done using least squares solving methods which are slow and adversely affected by local minima in the solvable surface. This thesis describes the development and implementation of a new technique using only Artificial Neural Networks (ANN) to calculate thin film parameters. The new method offers a speed in the orders of magnitude faster than preceding methods and convergence to local minima is completely eliminated.

Critério de correntropia no treinamento de redes fuzzy wavelet neural networks para identificação de sistemas dinâmicos não lineares

The great interest in nonlinear system identification is mainly due to the fact that a large amount of real systems are complex and need to have their nonlinearities considered so that their models can be successfully used in applications of control, prediction, inference, among others. This work evaluates the application of Fuzzy Wavelet Neural Networks (FWNN) to identify nonlinear dynamical systems subjected to noise and outliers. Generally, these elements cause negative effects on the identification procedure, resulting in erroneous interpretations regarding the dynamical behavior of the system. The FWNN combines in a single structure the ability to deal with uncertainties of fuzzy logic, the multiresolution characteristics of wavelet theory and learning and generalization abilities of the artificial neural networks. Usually, the learning procedure of these neural networks is realized by a gradient based method, which uses the mean squared error as its cost function. This work proposes the replacement of this traditional function by an Information Theoretic Learning similarity measure, called correntropy. With the use of this similarity measure, higher order statistics can be considered during the FWNN training process. For this reason, this measure is more suitable for non-Gaussian error distributions and makes the training less sensitive to the presence of outliers. In order to evaluate this replacement, FWNN models are obtained in two identification case studies: a real nonlinear system, consisting of a multisection tank, and a simulated system based on a model of the human knee joint. The results demonstrate that the application of correntropy as the error backpropagation algorithm cost function makes the identification procedure using FWNN models more robust to outliers. However, this is only achieved if the gaussian kernel width of correntropy is properly adjusted.

Neural networks would 'vote' according to Borda's Rule

Can neural networks learn to select an alternative based on a systematic aggregation of convicting individual preferences (i.e. a 'voting rule')? And if so, which voting rule best describes their behavior? We show that a prominent neural network can be trained to respect two fundamental principles of voting theory, the unanimity principle and the Pareto property. Building on this positive result, we train the neural network on profiles of ballots possessing a Condorcet winner, a unique Borda winner, and a unique plurality winner, respectively. We investigate which social outcome the trained neural network chooses, and find that among a number of popular voting rules its behavior mimics most closely the Borda rule. Indeed, the neural network chooses the Borda winner most often, no matter on which voting rule it was trained. Neural networks thus seem to give a surprisingly clear-cut answer to one of the most fundamental and controversial problems in voting theory: the determination of the most salient election method.

Application of multivariable control using artificial neural networks in a debutanizer distillation column

LOPES, Jose Soares Batista et al. Application of multivariable control using artificial neural networks in a debutanizer distillation column.In: INTERNATIONAL CONGRESS OF MECHANICAL ENGINEERING - COBEM, 19, 5-9 nov. 2007, Brasilia. Anais... Brasilia, 2007