Results 211 to 220 of about 66,291 (256)

Deep Neural Network-Based Algorithm Approximation via Multivariate Polynomial Regression

2019 IEEE Global Communications Conference (GLOBECOM), 2019
Many communication tasks have been formulated as optimization problems that can be solved by iterative algorithms. However, these algorithms are usually computationally intensive. To enable real-time processing of communication algorithms, in this paper, we propose a new deep neural network (DNN) architecture for algorithm approximation.
Chunmiao Liu, Bowen Shi, Chenglin Li, Junni Zou, Yingqi Chen, Hongkai Xiong   +5 more
openaire   +1 more source

The simultaneous approximation order of multivariate function by neural networks

International Conference on Automatic Control and Artificial Intelligence (ACAI 2012), 2012
In this document, we first give the order of simultaneous approximation of multivariate functions defined in simplex by multivariate Bernstein polynomials. Second, we prove that multivariate polynomials defined in simplex can be simultaneously approximated arbitrarily by a sigmoidal neural networks.
openaire   +1 more source

Pointwise and uniform approximation by multivariate neural network operators of the max-product type

Neural Networks, 2016
In this article, the theory of multivariate max-product neural network (NN) and quasi-interpolation operators has been introduced. Pointwise and uniform approximation results have been proved, together with estimates concerning the rate of convergence. At the end, several examples of sigmoidal activation functions have been provided.
Danilo Costarelli, Gianluca Vinti
openaire   +3 more sources

Approximations by Multivariate Perturbed Neural Networks

2015
This chapter deals with the determination of the rate of convergence to the unit of each of three newly introduced here multivariate perturbed normalized neural network operators of one hidden layer.
openaire   +1 more source

Multivariate Fuzzy Perturbed Neural Network Approximations

2015
This chapter studies the determination of the rate of convergence to the unit of each of three newly introduced here multivariate fuzzy perturbed normalized neural network operators of one hidden layer. These are given through the multivariate fuzzy modulus of continuity of the involved multivariate fuzzy number valued function or its high order fuzzy ...
openaire   +1 more source

Univariate Sigmoidal Neural Network Quantitative Approximation

2011
Here we present the multivariate quantitative constructive approximation of real and complex valued continuous multivariate functions on a box or ℝ N , N eℕ, by the multivariate quasi-interpolation sigmoidal neural network operators. The “hright” operators for the goal are fully and precisely described.
openaire   +1 more source

Multivariate Approximation With Rates by Perturbed Kantorovich-Shilkret Neural Network Operators

Sarajevo Journal of Mathematics, 2022
This paper deals with the determination of the rate of convergence to the unit of Perturbed Kantorovich-Shilkret multivariate normalized neural network operators of one hidden layer. These are given through the multivariate modulus of continuity of the engaged multivariate function or its high order partial derivatives and that appears in the ...
openaire   +1 more source

Multivariate Fuzzy-Random Normalized Neural Network Approximation

2015
In this chapter we study the rate of multivariate pointwise convergence in the q-mean to the Fuzzy-Random unit operator or its perturbation of very precise multivariate normalized Fuzzy-Random neural network operators of Cardaliaguet-Euvrard and “Squashing” types.
openaire   +1 more source

Multivariate Fuzzy-Random Perturbed Neural Network Approximations

2015
In this chapter we study the rate of multivariate pointwise and uniform convergences in the q-mean to the Fuzzy-Random unit operator of perturbed multivariate normalized Fuzzy-Random neural network operators of Stancu, Kantorovich and Quadrature types.
openaire   +1 more source

Multivariate Hyperbolic Tangent Neural Network Quantitative Approximation

2011
Here we give the multivariate quantitative approximation of real and complex valued continuous multivariate functions on a box or ℝ N , N eℕ, by the multivariate quasi-interpolation hyperbolic tangent neural network operators. This approximation is obtained by establishing multidimensional Jackson type inequalities involving the multivariate modulus of
openaire   +1 more source