Mixture density network training by computation in parameter space

Training Mixture Density Network (MDN) configurations within the NETLAB framework takes time due to the nature of the computation of the error function and the gradient of the error function. By optimising the computation of these functions, so that gradient information is computed in parameter space, training time is decreased by at least a factor of sixty for the example given. Decreased training time increases the spectrum of problems to which MDNs can be practically applied making the MDN framework an attractive method to the applied problem solver.

Network Training Services Ltd case study

Case study on developing a consistent and supportive approach to blended learning

On the differential evolution algorithm and its appliation to training radial basis function networks

The parameter setting of a differential evolution algorithm must meet several requirements: efficiency, effectiveness, and reliability. Problems vary. The solution of a particular problem can be represented in different ways. An algorithm most efficient in dealing with a particular representation may be less efficient in dealing with other representations. The development of differential evolution-based methods contributes substantially to research on evolutionary computing and global optimization in general. The objective of this study is to investigatethe differential evolution algorithm, the intelligent adjustment of its controlparameters, and its application. In the thesis, the differential evolution algorithm is first examined using different parameter settings and test functions. Fuzzy control is then employed to make control parameters adaptive based on an optimization process and expert knowledge. The developed algorithms are applied to training radial basis function networks for function approximation with possible variables including centers, widths, and weights of basis functions and both having control parameters kept fixed and adjusted by fuzzy controller. After the influence of control variables on the performance of the differential evolution algorithm was explored, an adaptive version of the differential evolution algorithm was developed and the differential evolution-based radial basis function network training approaches were proposed. Experimental results showed that the performance of the differential evolution algorithm is sensitive to parameter setting, and the best setting was found to be problem dependent. The fuzzy adaptive differential evolution algorithm releases the user load of parameter setting and performs better than those using all fixedparameters. Differential evolution-based approaches are effective for training Gaussian radial basis function networks.

HYBRID ARTIFICIAL NEURAL NETWORK APPLIEDTO MODELING SCFE OF BASIL AND ROSEMARY OILS

This work presents the results of a Hybrid Neural Network (HNN) technique as applied to modeling SCFE curves obtained from two Brazilian vegetable matrices. A series Hybrid Neural Network was employed to estimate the parameters of the phenomenological model. A small set of SCFE data of each vegetable was used to generate an extended data set, sufficient to train the network. Afterwards, other sets of experimental data, not used in the network training, were used to validate the present approach. The series HNN correlates well the experimental data and it is shown that the predictions accomplished with this technique may be promising for SCFE purposes.

Estimating microalgae Synechococcus nidulans daily biomass concentration using neuro-fuzzy network

In this study, a neuro-fuzzy estimator was developed for the estimation of biomass concentration of the microalgae Synechococcus nidulans from initial batch concentrations, aiming to predict daily productivity. Nine replica experiments were performed. The growth was monitored daily through the culture medium optic density and kept constant up to the end of the exponential phase. The network training followed a full 3³ factorial design, in which the factors were the number of days in the entry vector (3,5 and 7 days), number of clusters (10, 30 and 50 clusters) and internal weight softening parameter (Sigma) (0.30, 0.45 and 0.60). These factors were confronted with the sum of the quadratic error in the validations. The validations had 24 (A) and 18 (B) days of culture growth. The validations demonstrated that in long-term experiments (Validation A) the use of a few clusters and high Sigma is necessary. However, in short-term experiments (Validation B), Sigma did not influence the result. The optimum point occurred within 3 days in the entry vector, 10 clusters and 0.60 Sigma and the mean determination coefficient was 0.95. The neuro-fuzzy estimator proved a credible alternative to predict the microalgae growth.

A practical approach for training dynamic recurrent neural networks: use of Apriori information

Presents a technique for incorporating a priori knowledge from a state space system into a neural network training algorithm. The training algorithm considered is that of chemotaxis and the networks being trained are recurrent neural networks. Incorporation of the a priori knowledge ensures that the resultant network has behaviour similar to the system which it is modelling.

An application of neural network technique to correct the dome temperature effects on pyrgeometer measurements

This work describes an application of a multilayer perceptron neural network technique to correct dome emission effects on longwave atmospheric radiation measurements carried out using an Eppley Precision Infrared Radiometer (PIR) pyrgeometer. It is shown that approximately 7-month-long measurements of dome and case temperatures and meteorological variables available in regular surface stations (global solar radiation, air temperature, and air relative humidity) are enough to train the neural network algorithm and correct the observed longwave radiation for dome temperature effects in surface stations with climates similar to that of the city of São Paulo, Brazil. The network was trained using data from 15 October 2003 to 7 January 2004 and verified using data, not present during the network-training period, from 8 January to 30 April 2004. The longwave radiation values generated by the neural network technique were very similar to the values obtained by Fairall et al., assumed here as the reference approach to correct dome emission effects in PIR pyrgeometers. Compared to the empirical approach the neural network technique is less limited to sensor type and time of day (allows nighttime corrections).

Probabilistic neural network to predict cracks in taphole mud used in blast furnaces

One of the major problems facing Blast Furnaces is the occurrence of cracks in taphole mud, as the underlying causes are not easily identifiable. The absence of this knowledge makes it difficult the use of conventional techniques for predictability and mitigation. This paper will address the application of Probabilistic Neural Network using the Matlab software as a means to detect and control such cracks. The most relevant BF operational variables were picked through the statistic tool "Principal Component Analysis - PCA." Based upon the selection of these variables a probabilistic neural network was built. A set of BF operational data, consisting of 30 controlling variables, was divided into 2 groups, one of which for network training, and the other one to validate the neural network. The neural network got 98% of the cases right. The results show the effectiveness of this tool for crack prediction in relation to clay intrinsic properties and as a result of the fluctuation in operational variables.

Neural networks training using the constructivism paradigms

The Backpropagation Algorithm (BA) is the standard method for training multilayer Artificial Neural Networks (ANN), although it converges very slowly and can stop in a local minimum. We present a new method for neural network training using the BA inspired on constructivism, an alphabetization method proposed by Emilia Ferreiro based on Piaget philosophy. Simulation results show that the proposed configuration usually obtains a lower final mean square error, when compared with the standard BA and with the BA with momentum factor.

Training with noise is equivalent to Tikhonov regularization

It is well known that the addition of noise to the input data of a neural network during training can, in some circumstances, lead to significant improvements in generalization performance. Previous work has shown that such training with noise is equivalent to a form of regularization in which an extra term is added to the error function. However, the regularization term, which involves second derivatives of the error function, is not bounded below, and so can lead to difficulties if used directly in a learning algorithm based on error minimization. In this paper we show that, for the purposes of network training, the regularization term can be reduced to a positive definite form which involves only first derivatives of the network mapping. For a sum-of-squares error function, the regularization term belongs to the class of generalized Tikhonov regularizers. Direct minimization of the regularized error function provides a practical alternative to training with noise.

A Bayesian neural network algorithm identifies patients in whom post-EVAR surveillance may be unnecessary

Lifelong surveillance is not cost-effective after endovascular aneurysm repair (EVAR), but is required to detect aortic complications which are fatal if untreated (type 1/3 endoleak, sac expansion, device migration). Aneurysm morphology determines the probability of aortic complications and therefore the need for surveillance, but existing analyses have proven incapable of identifying patients at sufficiently low risk to justify abandoning surveillance. This study aimed to improve the prediction of aortic complications, through the application of machine-learning techniques. Patients undergoing EVAR at 2 centres were studied from 2004–2010. Aneurysm morphology had previously been studied to derive the SGVI Score for predicting aortic complications. Bayesian Neural Networks were designed using the same data, to dichotomise patients into groups at low- or high-risk of aortic complications. Network training was performed only on patients treated at centre 1. External validation was performed by assessing network performance independently of network training, on patients treated at centre 2. Discrimination was assessed by Kaplan-Meier analysis to compare aortic complications in predicted low-risk versus predicted high-risk patients. 761 patients aged 75 +/− 7 years underwent EVAR in 2 centres. Mean follow-up was 36+/− 20 months. Neural networks were created incorporating neck angu- lation/length/diameter/volume; AAA diameter/area/volume/length/tortuosity; and common iliac tortuosity/diameter. A 19-feature network predicted aor- tic complications with excellent discrimination and external validation (5-year freedom from aortic complications in predicted low-risk vs predicted high-risk patients: 97.9% vs. 63%; p < 0.0001). A Bayesian Neural-Network algorithm can identify patients in whom it may be safe to abandon surveillance after EVAR. This proposal requires prospective study.

Artificial neural networks analysis of Sao Paulo subway tunnel settlement data

Artificial neural networks have been used to analyze a number of engineering problems, including settlement caused by different tunneling methods in various types of ground mass. This paper focuses on settlement over shotcrete- supported tunnels on Sao Paulo subway line 2 (West Extension) that were excavated in Tertiary sediments using the sequential excavation method. The adjusted network is a good tool for predicting settlement above new tunnels to be excavated in similar conditions. The influence of network training parameters on the quality of results is also discussed. (C) 2007 Elsevier Ltd. All rights reserved.

Entre imagens cinema e imagens escola, movimentando o pensamento com a formação de professores

A presente pesquisa aborda o estudo dos movimentos do pensamento nas redes formação com professores no Ensino Fundamental. Procura problematizar a constituição de processos formativos não dogmáticos nos cotidianos escolares, pela articulação de imagens cinema e imagens escola, exibidas, compartilhadas e criadas nas redes de conversações em uma escola municipal de Vitória/ES, entre os anos de 2013 a 2014. Apresenta um campo problemático que se dedica a compreender que movimentos do pensamento são produzidos a partir do uso de imagens cinema nas redes de conversações com professores em formação continuada, a partir de uma cartografia de pesquisa que articula o mapeamento de virtualidades presentes no banco de teses da CAPES e as cinecartografias do cotidiano escolar em duas dobras do tempo. Tece um debate teórico que se compõe pelas linhas de pensamento, principalmente, de Bergson (2006a; 2006b), Carvalho (2008; 2009; 2010; 2012) Deleuze (1988; 1991; 1992; 1995; 1996; 2003; 2006; 2007; 2010; 2011), Foucault (1979; 1999. 2006a; 2006b; 2008), Guéron (2010; 2011), Pelbart (2011), Sauvagnargues (2009), dentre outros. As opções teórico-metodológicas estabelecem uma pesquisa de campo na intercessão entre os estudos com o cotidiano escolar e os da pesquisa cartográfica, tomando o plano de imanência como mundo material para a ocorrência de acontecimentos. Utiliza, para a produção de dados a observação participante, os registros em diário de campo, considerados como uma descrição cristalina, assim como, as narrativas cristalinas que emergiam nas redes de conversações com as personagens-escolas (docentes), que se configuram como imagensnarrativas de pesquisa. Organiza o debate dos dados produzidos em sete capítulos. Apresenta como considerações três principais agrupamentos do movimento do pensamento nas redes de conversações com professores provocados pelas imagens cinema: cinescola-clichês, imagensformação docente e cristaisescolas. Destaca que não há uma realidade que comporte uma só verdade sobre a formação com professores, mas o que existe são cortes, percepções, afecções e produções de verdades que entrelaçam os diferentes modos de existir e reexistir na educação brasileira. As telasescolas, assim como as telas do cinema, apresentam e nos cercam com um mundo que articula um cinescola-clichê, imagensformação docente e cristaisescolas, que para além do pensamento reto e dogmático, exibem entre imagens cinema e imagens escolas, outros movimentos do pensamento com a formação de professores, sendo capazes de potencializar as pesquisas educacionais a não ir em ‘busca de um tempo perdido, mas de um tempo a ser redescoberto’, fazendo crer ainda mais nesse mundo e na educação.

Predicting chick body mass by artificial intelligence-based models

The objective of this work was to develop, validate, and compare 190 artificial intelligence-based models for predicting the body mass of chicks from 2 to 21 days of age subjected to different duration and intensities of thermal challenge. The experiment was conducted inside four climate-controlled wind tunnels using 210 chicks. A database containing 840 datasets (from 2 to 21-day-old chicks) - with the variables dry-bulb air temperature, duration of thermal stress (days), chick age (days), and the daily body mass of chicks - was used for network training, validation, and tests of models based on artificial neural networks (ANNs) and neuro-fuzzy networks (NFNs). The ANNs were most accurate in predicting the body mass of chicks from 2 to 21 days of age after they were subjected to the input variables, and they showed an R² of 0.9993 and a standard error of 4.62 g. The ANNs enable the simulation of different scenarios, which can assist in managerial decision-making, and they can be embedded in the heating control systems.

Artificial neural networks (ANN): prediction of sensory measurements from instrumental data

The objective of this study was to predict by means of Artificial Neural Network (ANN), multilayer perceptrons, the texture attributes of light cheesecurds perceived by trained judges based on instrumental texture measurements. Inputs to the network were the instrumental texture measurements of light cheesecurd (imitative and fundamental parameters). Output variables were the sensory attributes consistency and spreadability. Nine light cheesecurd formulations composed of different combinations of fat and water were evaluated. The measurements obtained by the instrumental and sensory analyses of these formulations constituted the data set used for training and validation of the network. Network training was performed using a back-propagation algorithm. The network architecture selected was composed of 8-3-9-2 neurons in its layers, which quickly and accurately predicted the sensory texture attributes studied, showing a high correlation between the predicted and experimental values for the validation data set and excellent generalization ability, with a validation RMSE of 0.0506.