Abstract
Here we study the multivariate quantitative approximation of Banach space valued continuous multivariate functions on a box or \(\mathbb {R}^{N}\), \(N\in \mathbb {N},\) by the multivariate normalized, quasi-interpolation, Kantorovich type and quadrature type neural network operators. We research also the case of approximation by iterated multilayer neural network operators of the last four types. These approximations are achieved by establishing multidimensional Jackson type inequalities involving the multivariate modulus of continuity of the engaged function or its high order Fréchet derivatives or partial derivatives. Our multivariate operators are defined by using a multidimensional density function induced by a q-deformed hyperbolic tangent sigmoid function. The approximations are pointwise and uniform. The related feed-forward neural network are with one or multi hidden layers.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anastassiou, G.A.: Moments in Probability and Approximation Theory. Pitman Research Notes in Mathematics, vol. 287. Longman Scientific & Technical, Harlow (1993)
Anastassiou, G.A.: Rate of convergence of some neural network operators to the unit-univariate case. J. Math. Anal. Appl. 212, 237–262 (1997)
Anastassiou, G.A.: Quantitative Approximations. Chapman & Hall/CRC, Boca Raton, New York (2001)
Anastassiou, G.A.: Intelligent Systems: Approximation by Artificial Neural Networks. Intelligent Systems Reference Library, vol. 19. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21431-8
Anastassiou, G.A.: Univariate hyperbolic tangent neural network approximation. Math. Comput. Model. 53, 1111–1132 (2011)
Anastassiou, G.A.: Multivariate hyperbolic tangent neural network approximation. Comput. Math. 61, 809–821 (2011)
Anastassiou, G.A.: Multivariate sigmoidal neural network approximation. Neural Netw. 24, 378–386 (2011)
Anastassiou, G.A.: Univariate sigmoidal neural network approximation. J. Comput. Anal. Appl. 14(4), 659–690 (2012)
Anastassiou, G.A.: Approximation by neural networks iterates. In: Anastassiou, G., Duman, O. (eds.) Advances in Applied Mathematics and Approximation Theory. Springer Proceedings in Mathematics & Statistics, vol. 41, pp. 1–20. Springer, New York (2013). https://doi.org/10.1007/978-1-4614-6393-1_1
Anastassiou, G.: Intelligent Systems II: Complete Approximation by Neural Network Operators. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-319-20505-2
Anastassiou, G.: Intelligent Computations: Abstract Fractional Calculus, Inequalities, Approximations. Springer, Heidelberg (2018). https://doi.org/10.1007/978-3-319-66936-6
Anastassiou, G.A.: Banach Space Valued Neural Network. Springer, Heidelberg (2023). https://doi.org/10.1007/978-3-031-16400-2
Anastassiou, G.A.: \(q\)-Deformed hyperbolic tangent based Banach space valued ordinary and fractional neural network approximations. Rev. Real Acad. Cienc. Exactas Fis. Nat. Ser. A-Mat. 117, 83 (2023)
Cartan, H.: Differential Calculus. Hermann, Paris (1971)
Chen, Z., Cao, F.: The approximation operators with sigmoidal functions. Comput. Math. Appl. 58, 758–765 (2009)
Costarelli, D., Spigler, R.: Approximation results for neural network operators activated by sigmoidal functions. Neural Netw. 44, 101–106 (2013)
Costarelli, D., Spigler, R.: Multivariate neural network operators with sigmoidal activation functions. Neural Netw. 48, 72–77 (2013)
El-Shehawy, S.A., Abdel-Salam, E.A.-B.: The \(q\)-deformed hyperbolic Secant family. Int. J. Appl. Math. Stat. 29(5), 51–62 (2012)
Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice Hall, New York (1998)
McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 7, 115–133 (1943)
Mitchell, T.M.: Machine Learning. WCB-McGraw-Hill, New York (1997)
Rall, L.B.: Computational Solution of Nonlinear Operator Equations. Wiley, New York (1969)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Anastassiou, G.A. (2024). q-Deformed Hyperbolic Tangent Relied Banach Space Valued Multivariate Multi Layer Neural Network Approximation. In: Singh, J., Anastassiou, G.A., Baleanu, D., Kumar, D. (eds) Advances in Mathematical Modelling, Applied Analysis and Computation . ICMMAAC 2023. Lecture Notes in Networks and Systems, vol 953. Springer, Cham. https://doi.org/10.1007/978-3-031-56304-1_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-56304-1_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56303-4
Online ISBN: 978-3-031-56304-1
eBook Packages: EngineeringEngineering (R0)