Results 31 to 40 of about 43,273 (183)
Estimation of Approximating Rate for Neural Network inLwp Spaces
A class of Soblove type multivariate function is approximated by feedforward network with one hidden layer of sigmoidal units and a linear output. By adopting a set of orthogonal polynomial basis and under certain assumptions for the governing activation
Jian-Jun Wang, Chan-Yun Yang, Jia Jing
doaj +1 more source
Mild Pretreatments to Increase Fructose Consumption in Saccharomyces cerevisiae Wine Yeast Strains
The present research investigates the effect of different pretreatments on glucose and fructose consumption and ethanol production by four Saccharomyces cerevisiae wine strains, three isolated and identified from different wine regions in Turkey and one ...
Hatice Aybuke Karaoglan +3 more
doaj +1 more source
Constructive Approximation by Superposition of Sigmoidal Functions
In this paper, a constructive theory is developed for approximating func- tions of one or more variables by superposition of sigmoidal functions. This is done in the uniform norm as well as in the L p norm. Results for the simultaneous approx- imation, with the same order of accuracy, of a function and its derivatives (whenever these exist), are ...
COSTARELLI, DANILO, SPIGLER, Renato
openaire +1 more source
Approximation properties of some two-layer feedforward neural networks [PDF]
In this article, we present a multivariate two-layer feedforward neural networks that approximate continuous functions defined on \([0,1]^d\). We show that the \(L_1\) error of approximation is asymptotically proportional to the modulus of continuity of ...
Michał A. Nowak
doaj
APPLICATIONS OF SOME NEW TRANSMUTED CUMULATIVE DISTRIBUTION FUNCTIONS IN POPULATION DYNAMICS
Motivation: In literature, several transformations exists to obtain a new cumulative distribution function (cdf) using other(s) well-known cdf(s). Results: In this note we find applications of some new cumulative distribution function transformations ...
Vesselin Kyurkchiev +2 more
doaj +1 more source
Radius Constants of Sigmoid Starlike Functions
In the present investigation, we study the class of Sigmoid starlike functions, given by $\mathcal{S}^*_{SG}=\{f\in\mathcal{A}: {zf'(z)}/{f(z)}\prec 2/(1+e^{-z})\}$ in context of estimating the sharp radius constants associated with several known subclasses of starlike functions.
Goel, Priyanka, Kumar, S. Sivaprasad
openaire +2 more sources
Applications of Modified Sigmoid Functions to a Class of Starlike Functions [PDF]
The main focus of this investigation is the applications of modified sigmoid functions. Due to its various uses in physics, engineering, and computer science, we discuss several geometric properties like necessary and sufficient conditions in the form of convolutions for functions to be in the special classSSG∗earlier introduced by Goel and Kumar and ...
Muhammad Ghaffar Khan +4 more
openaire +3 more sources
On attracting sets in artificial networks: cross activation
Mathematical models of artificial networks can be formulated in terms of dynamical systems describing the behaviour of a network over time. The interrelation between nodes (elements) of a network is encoded in the regulatory matrix.
Sadyrbaev Felix
doaj +1 more source
Some properties of the Blumberg's hyper-log-logistic curve
The paper considers the sigmoid function definedthrough the hyper-log-logistic model introduced by Blumberg. We study the Hausdorff distance of this sigmoid to the Heaviside function, which characterises the shape of switching from 0 to 1.
Roumen Anguelov +2 more
doaj +1 more source
Equivalent Analytical Functions of Sums of Sigmoid like Transcendental Functions [PDF]
Abstract There is no mathematical solution to adding up transcendental functions other than numerical process. This paper put forward analytical method to model the sum of sigmoid like functions with an equivalent function. The Brillouin and Langevin as well as the error function, the tanh, sigmoid and the tan-
openaire +2 more sources

