• Journal of applied mathematics & informatics
• /
• v.5 no.3
• /
• pp.867-875
• /
• 1998

In this paper we prove that any continuous function on a bounded closed interval of can be approximated by the superposition of a bounded sigmoidal function with a fixed weight. In addition we show that any continuous function over $\mathbb{R}$ which vanishes at infinity can be approximated by the superposition f a bounded sigmoidal function with a weighted norm. Our proof is constructive.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.107-115
• /
• 2006

This paper presents a new class of activation functions for Cascade Correlation learning algorithm, which herein will be called CosGauss function. This function is a cosine modulated gaussian function. In contrast to the sigmoidal, hyperbolic tangent and gaussian functions, more ridges can be obtained by the CosGauss function. Because of the ridges, it is quickly convergent and improves a pattern recognition speed. Consequently it will be able to improve a learning capability. This function was tested with a Cascade Correlation Network on the two spirals problem and results are compared with those obtained with other activation functions.

• International Journal of Highway Engineering
• /
• v.10 no.4
• /
• pp.31-40
• /
• 2008

The dynamic moduli of asphalt concrete are very important for the analysis and the design of asphalt pavement systems. The dynamic modulus master curve is usually represented by a sigmoidal function. The Ramberg-Osgood model was widely used for fitting of normalized modulus reduction curves with strain of soils in soil dynamic fields. The master curves were obtained by both sigmoidal functions and modified Ramberg-Osgood model for the same dynamic modulus data set, the fitting abilities of both methods were excellent. The coefficients in sigmoidal function are coupled. Therefore, it is not possible to separate the characteristics of the master curve with absolute value and shape. However, the each fitting coefficient in the Ramberg-Osgood model has a unique effect on the master curve, and the coefficients are not coupled with each other.

• Nuclear Engineering and Technology
• /
• v.53 no.1
• /
• pp.258-265
• /
• 2021

High levels for noise and a loss of true signal make the quantitative interpretation of nuclear medicine (NM) images difficult. An application of profile optimization using a sigmoidal function in this study was used to acquire the NM images with high quality. And the images were acquired by using three kinds of reconstruction method using each same sinogram: a standard filtered back-projection (FBP), an iterative reconstruction (IR) technique, and the sigmoidal function profile optimization (SFPO). Comparison of image according to reconstruction method was performed to show a superiority of the SFPO for imaging. The images reconstructed by using the SFPO showed an average of 1.49 times and of 1.17 times better in contrast than the results obtained using the standard FBP and the IR technique, respectively. Higher signal to noise ratios were obtained as an average of 12.30 times and of 3.77 times than results obtained using the standard FBP and the IR technique, respectively. This study confirms that reconstruction with SFPO (vs FBP and vs IR) can lead to better lesion detectability and characterization with noise reduction. It can be developed for future reconstruction technique for the NM imaging.

• Honam Mathematical Journal
• /
• v.27 no.2
• /
• pp.225-232
• /
• 2005

We obtain the approximation order to a smooth function on a compact subset of $\mathbb{R}$ by generalized translation networks. In our study, the activation function is infinitely many times continuously differentiable function but it does not have special properties around ${\infty}$ and $-{\infty}$ like a sigmoidal activation function. Using the Jackson's Theorem, we get the approximation order. Especially, we obtain the approximation order by a neural network with a fixed threshold.

• Advances in materials Research
• /
• v.12 no.1
• /
• pp.43-65
• /
• 2023

Free vibration analysis of power law and sigmoidal sandwich plates made up of functionally graded materials (FGMs) has been carried out using finite element based higher-order zigzag theory. The present model satisfies all-important conditions such as transverse shear stress-free conditions at the plate's top and bottom surface along with continuity condition for transverse stresses at the interface. A Nine-noded C0 finite element having eleven degrees of freedom per node is used during the study. The present model is free from the requirement of any penalty function or post-processing technique and hence is computationally efficient. The present model's effectiveness is demonstrated by comparing the present results with available results in the literature. Several new results have been proposed in the present work, which will serve as a benchmark for future works. It has been observed that the material variation law, power-law exponent, skew angle, and boundary condition of the plate widely determines the free vibration behavior of sandwich functionally graded (FG) plate.

• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.97-105
• /
• 2009

This paper presents a combination of the generalized Cascade Correlation and generalized Recurrent Cascade Correlation learning algorithms. The new network will be able to grow with vertical or horizontal direction and with recurrent or without recurrent units for the quick solution of the pattern classification problem. The proposed algorithm was tested learning capability with the sigmoidal activation function and hyperbolic tangent activation function on the contact lens and balance scale standard benchmark problems. And results are compared with those obtained with Cascade Correlation and Recurrent Cascade Correlation algorithms. By the learning the new network was composed with the minimal number of the created hidden units and shows quick learning speed. Consequently it will be able to improve a learning capability.

• Honam Mathematical Journal
• /
• v.28 no.1
• /
• pp.125-133
• /
• 2006

We investigate the approximation order to a function in $L_p$[-1, 1] for $0{\leq}p<{\infty}$ by generalized translation networks. In most papers related to neural network approximation, sigmoidal functions are adapted as an activation function. In our research, we choose an infinitely many times continuously differentiable function as an activation function. Using the integral modulus of continuity and the divided difference formula, we get the approximation order to a function in $L_p$[-1, 1].

• Korean Journal of Mathematics
• /
• v.23 no.3
• /
• pp.327-336
• /
• 2015

In this paper, we study a constructive approximation by neural networks with positive integer weights. Like neural networks with real weights, we show that neural networks with positive integer weights can even approximate arbitrarily well for any continuous functions on compact subsets of $\mathbb{R}$. We give a numerical result to justify our theoretical result.

• Structural Engineering and Mechanics
• /
• v.66 no.1
• /
• pp.85-96
• /
• 2018

This study investigates the response of functionally graded (FG) gas pipe under unsteady internal pressure and temperature. The pipe is proposed to be manufactured from FGMs rather than custom carbon steel, to reduce the erosion, corrosion, pressure surge and temperature variation effects caused by conveying of gases. The distribution of material graduations are obeying power and sigmoidal functions varying with the pipe thickness. The sigmoidal distribution is proposed for the 1st time in analysis of FG pipe structure. A Two-dimensional (2D) plane strain problem is proposed to model the pipe cross-section. The Fourier law is applied to describe the heat flux and temperature variation through the pipe thickness. The time variation of internal pressure is described by using exponential-harmonic function. The proposed problem is solved numerically by a two-dimensional (2D) plane strain finite element ABAQUS software. Nine-node isoparametric element is selected. The proposed model is verified with published results. The effects of material graduation, material function, temperature and internal pressures on the response of FG gas pipe are investigated. The coupled temperature and displacement FEM solution is used to find a solution for the stress displacement and temperature fields simultaneously because the thermal and mechanical solutions affected greatly by each other. The obtained results present the applicability of alternative FGM materials rather than classical A106Gr.B steel. According to proposed model and numerical results, the FGM pipe is more effective in natural gas application, especially in eliminating the corrosion, erosion and reduction of stresses.