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.

Activation function study for wavelet network

The main purpose of this paper is to investigate theoretically and experimentally the use of family of Polynomial Powers of the Sigmoid (PPS) Function Networks applied in speech signal representation and function approximation. This paper carries out practical investigations in terms of approximation fitness (LSE), time consuming (CPU Time), computational complexity (FLOP) and representation power (Number of Activation Function) for different PPS activation functions. We expected that different activation functions can provide performance variations and further investigations will guide us towards a class of mappings associating the best activation function to solve a class of problems under certain criteria.

Approximation of hyperbolic tangent activation function using hybrid methods

Artificial Neural Networks are widely used in various applications in engineering, as such solutions of nonlinear problems. The implementation of this technique in reconfigurable devices is a great challenge to researchers by several factors, such as floating point precision, nonlinear activation function, performance and area used in FPGA. The contribution of this work is the approximation of a nonlinear function used in ANN, the popular hyperbolic tangent activation function. The system architecture is composed of several scenarios that provide a tradeoff of performance, precision and area used in FPGA. The results are compared in different scenarios and with current literature on error analysis, area and system performance. © 2013 IEEE.

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.

Human face verification based on multidimensional Polynomial Powers of Sigmoid (PPS)

In this paper, we described how a multidimensional wavelet neural networks based on Polynomial Powers of Sigmoid (PPS) can be constructed, trained and applied in image processing tasks. In this sense, a novel and uniform framework for face verification is presented. The framework is based on a family of PPS wavelets,generated from linear combination of the sigmoid functions, and can be considered appearance based in that features are extracted from the face image. The feature vectors are then subjected to subspace projection of PPS-wavelet. The design of PPS-wavelet neural networks is also discussed, which is seldom reported in the literature. The Stirling Universitys face database were used to generate the results. Our method has achieved 92 % of correct detection and 5 % of false detection rate on the database.

Identificação e controle de sistemas dinâmicos utilizando redes wavelets

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

BASIC HYPERGEOMETRIC FUNCTIONS and ORTHOGONAL LAURENT POLYNOMIALS

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Stieltjes functions and discrete classical orthogonal polynomials

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Parametric correlation functions to model the structure of permanent environmental (co)variances in milk yield random regression models

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Covariance functions for body weight from birth to maturity in Nellore cows

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Random regression analyses using B-splines functions to model growth from birth to adult age in Canchim cattle

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Random regression analyses using B-spline functions to model growth of Nellore cattle

The objective of this study was to estimate (co)variance components using random regression on B-spline functions to weight records obtained from birth to adulthood. A total of 82 064 weight records of 8145 females obtained from the data bank of the Nellore Breeding Program (PMGRN/Nellore Brazil) which started in 1987, were used. The models included direct additive and maternal genetic effects and animal and maternal permanent environmental effects as random. Contemporary group and dam age at calving (linear and quadratic effect) were included as fixed effects, and orthogonal Legendre polynomials of age (cubic regression) were considered as random covariate. The random effects were modeled using B-spline functions considering linear, quadratic and cubic polynomials for each individual segment. Residual variances were grouped in five age classes. Direct additive genetic and animal permanent environmental effects were modeled using up to seven knots (six segments). A single segment with two knots at the end points of the curve was used for the estimation of maternal genetic and maternal permanent environmental effects. A total of 15 models were studied, with the number of parameters ranging from 17 to 81. The models that used B-splines were compared with multi-trait analyses with nine weight traits and to a random regression model that used orthogonal Legendre polynomials. A model fitting quadratic B-splines, with four knots or three segments for direct additive genetic effect and animal permanent environmental effect and two knots for maternal additive genetic effect and maternal permanent environmental effect, was the most appropriate and parsimonious model to describe the covariance structure of the data. Selection for higher weight, such as at young ages, should be performed taking into account an increase in mature cow weight. Particularly, this is important in most of Nellore beef cattle production systems, where the cow herd is maintained on range conditions. There is limited modification of the growth curve of Nellore cattle with respect to the aim of selecting them for rapid growth at young ages while maintaining constant adult weight.

Random regression models using different functions to model test-day milk yield of Brazilian Holstein cows

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Increased pancreatic islet mass is accompanied by activation of the insulin receptor substrate-2/serine-threonine kinase pathway and augmented cyclin D(2) protein levels in insulin-resistant rats

It is well known that glucocorticoids induce peripheral insulin resistance in rodents and humans. Here, we investigated the structural and ultrastructural modifications, as well as the proteins involved in beta-cell function and proliferation, in islets from insulin-resistant rats. Adult male Wistar rats were made insulin resistant by daily administration of dexamethasone (DEX; 1mg/kg, i.p.) for five consecutive days, whilst control (CTL) rats received saline alone. Structure analyses showed a marked hypertrophy of DEX islets with an increase of 1.7-fold in islet mass and of 1.6-fold in islet density compared with CTL islets (P < 0.05). Ultrastructural evaluation of islets revealed an increased amount of secreting organelles, such as endoplasmic reticulum and Golgi apparatus in DEX islets. Mitotic figures were observed in DEX islets at structural and ultrastructural levels. Beta-cell proliferation, evaluated at the immunohistochemical level using anti-PCNA (proliferating cell nuclear antigen), showed an increase in pancreatic beta-cell proliferation of 6.4-fold in DEX islets compared with CTL islets (P < 0.0001). Increases in insulin receptor substrate-2 (IRS-2), phosphorylated-serine-threonine kinase AKT (p-AKT), cyclin D(2) and a decrease in retinoblastoma protein (pRb) levels were observed in DEX islets compared with CTL islets (P < 0.05). Therefore, during the development of insulin resistance, the endocrine pancreas adapts itself increasing beta-cell mass and proliferation, resulting in an amelioration of the functions. The potential mechanisms that underlie these events involve the activation of the IRS-2/AKT pathway and activation of the cell cycle, mediated by cyclin D(2). These adaptations permit the maintenance of glycaemia at near-physiological ranges.

ROLE of TLR2 and TLR4 on human neutrophil functions against Paracoccidioides brasiliensis

In paracoccidioidomycosis, a systemic mycosis caused by the fungus Paracoccidioides brasiliensis (Pb), studies have focused on the role of neutrophils that are involved in the primary response to the fungus. Neutrophil functions are regulated by pro- and anti-inflammatory cytokines. Molecular mechanisms involved in this process are not fully understood, but there are strong evidences about the involvement of toll-like receptors (TLRs). We aimed at evaluating TLR2 and TLR4 expression on human neutrophils activated by GM-CSF, IL-15, TNF-alpha or IFNgamma and challenged with a virulent strain of P. brasiliensis (Pb18). Moreover, we asked if these receptors have a role on fungicidal activity, H(2)O(2) and IL-6, IL-8, TNFalpha and IL-10 production, by activating and challenging cells. All cytokines increased TLR2 and TLR4 expression. Pb18 also increased TLR2 expression, inducing an additional cytokine effect. on the contrary, it inhibited TLR4 expression. All cytokines increased neutrophil fungicidal activity and H(2)O(2) production; however, this process was not associated with TLR2 or TLR4. Neutrophil activation by GMCSF and TNF-alpha resulted in a significant increase of IL-8 production, while IL-15 and IFN-alpha have no effect. Pb18 also augmented IL-8 expression, inducing an additional effect to that of cytokines. None of the cytokines activated neutrophils by releasing IL-10. This cytokine was only detected after Pb18 challenge. Interestingly, IL-8 and IL-10 production involved TLR2 and mainly TLR4 modulation. The present results suggest that Pb18 interaction with neutrophils through TLR2 and TLR4 with consequent IL-8 and IL-10 production may be considered a pathogenic mechanism in paracoccidioidomycosis.