Papers in Refereed Journals
(with A. Ismayilova) On the Kolmogorov neural networks, Neural Networks 176 (2024), Paper No. 106333, https://doi.org/10.1016/j.neunet.2024.106333
Approximation error of single hidden layer neural networks with fixed weights, Information Processing Letters 185 (2024), Paper No. 106467, doi.org/10.1016/j.ipl.2023.106467
(with A.Kh. Asgarova and A.A. Huseynli) A Chebyshev-type alternation theorem for best approximation by a sum of two algebras, Proceedings of the Edinburgh Mathematical Society (2) 66 (2023), no. 4, 971-978, doi.org/10.1017/S0013091523000494
(with R.A. Aliev and A.A. Asgarova) The double difference property for the class of locally Hölder continuous functions, Moscow Mathematical Journal 22 (2022), no. 3, 393-400, http://www.mathjournals.org/mmj/2022-022-003/2022-022-003-002.html
(with R.A. Aliev and A.A. Asgarova) On the representation by bivariate ridge functions, Ukrainian Mathematical Journal 73 (2021), no. 5, 675-685, https://doi.org/10.1007/s11253-021-01952-9
(with A.Kh. Asgarova) A Chebyshev-type theorem characterizing best approximation of a continuous function by elements of the sum of two algebras, (Russian) Mat. Zametki 109 (2021), no. 1, 19-26; English transl. in Mathematical Notes 109 (2021), 15-20, https://doi.org/10.1134/S0001434621010028
(with R.A. Aliev) A representation problem for smooth sums of ridge functions, Journal of Approximation Theory 257 (2020), 105448, 13 pp, https://doi.org/10.1016/j.jat.2020.105448
(with R.A. Aliev and A.A. Asgarova) On the Hölder continuity in ridge function representation, Proc. Inst. Math. Mech. Natl. Acad. Sci. Azerb. 45 (2019), no. 1, 31-40, http://proc.imm.az/volumes/45-1/45-01-03.pdf
Computing the approximation error for neural networks with weights varying on fixed directions, Numerical Functional Analysis and Optimization 40 (2019), no. 12, 1395-1409, https://doi.org/10.1080/01630563.2019.1605523
(with R.A. Aliev and A.A. Asgarova) A note on continuous sums of ridge functions, Journal of Approximation Theory 237 (2019), 210-221, https://doi.org/10.1016/j.jat.2018.09.006
(with N. Guliyev) Approximation capability of two hidden layer feedforward neural networks with fixed weights, Neurocomputing 316 (2018), 262-269, https://doi.org/10.1016/j.neucom.2018.07.075
(with N. Guliyev) On the approximation by single hidden layer feedforward neural networks with fixed weights, Neural Networks 98 (2018), 296-304, https://doi.org/10.1016/j.neunet.2017.12.007
A note on the criterion for a best approximation by superpositions of functions, Studia Mathematica 240 (2018), no. 2, 193-199, https://doi.org/10.4064/sm170314-9-4
(with A.Kh. Asgarova) On the representation by sums of algebras of continuous functions, Comptes Rendus Mathematique 355 (2017), no. 9, 949-955, https://doi.org/10.1016/j.crma.2017.09.015
A note on the equioscillation theorem for best ridge function approximation, Expositiones Mathematicae 35 (2017), no. 3, 343-349, https://doi.org/10.1016/j.exmath.2017.05.003
(with A.Kh. Asgarova) Diliberto–Straus algorithm for the uniform approximation by a sum of two algebras, Proceedings - Mathematical Sciences 127 (2017), no. 2, 361-374, http://dx.doi.org/10.1007/s12044-017-0337-4
(with E. Savas) Measure theoretic results for approximation by neural networks with limited weights, Numerical Functional Analysis and Optimization 38 (2017), no. 7, 819-830, http://dx.doi.org/10.1080/01630563.2016.1254654
Approximation by sums of ridge functions with fixed directions, (Russian) Algebra i Analiz 28 (2016), no. 6, 20–69, http://mi.mathnet.ru/eng/aa1513 English transl. St. Petersburg Mathematical Journal 28 (2017), 741-772, https://doi.org/10.1090/spmj/1471
On the uniqueness of representation by linear superpositions, Ukrainskii Matematicheskii Zhurnal 68 (2016), no. 12, 1620-1628. English transl. Ukrainian Mathematical Journal 68 (2017), no. 12, 1874-1883, https://doi.org/10.1007/s11253-017-1335-5
(with N. Guliyev) A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function, Neural Computation 28 (2016), no. 7, 1289–1304, http://dx.doi.org/10.1162/NECO_a_00849
(with R. Aliev) On a smoothness problem in ridge function representation, Advances in Applied Mathematics 73 (2016), 154--169, http://dx.doi.org/10.1016/j.aam.2015.11.002
(with R. Aliev and T. Shahbalayeva) On the representation by sums of ridge functions, Proc. Inst. Math. Mech. Natl. Acad. Sci. Azerb. 41 (2015), no. 2, 106--118, http://proc.imm.az/volumes/41-2/41-02-10.pdf
Alternating algorithm for the approximation by sums of two compositions and ridge functions, Proc. Inst. Math. Mech. Natl. Acad. Sci. Azerb. 41 (2015), no. 1, 146--152, http://www.proc.imm.az/volumes/41-1/41-01-15.pdf
Approximation by ridge functions and neural networks with a bounded number of neurons, Applicable Analysis 94 (2015), no. 11, 2245-2260,
On the approximation by neural networks with bounded number of neurons in hidden layers, Journal of Mathematical Analysis and Applications 417 (2014), no. 2, 963--969, http://dx.doi.org/10.1016/j.jmaa.2014.03.092
(with A. Pinkus) Interpolation on lines by ridge functions, Journal of Approximation Theory 175 (2013), 91-113, http://dx.doi.org/10.1016/j.jat.2013.07.010
A review of some results on ridge function approximation, Azerbaijan Journal of Mathematics 3 (2013), no.1, 3-51, http://azjm.org/index.php/azjm/article/view/143
Approximation by neural networks with weights varying on a finite set of directions, Journal of Mathematical Analysis and Applications 389 (2012), Issue 1, 72-83, http://dx.doi.org/10.1016/j.jmaa.2011.11.037
A note on the representation of continuous functions by linear superpositions, Expositiones Mathematicae 30 (2012), Issue 1, 96-101, http://dx.doi.org/10.1016/j.exmath.2011.07.005
Approximation by Neural Networks with a Restricted Set of Weights, book chapter, in: Advances in Mathematics Research (published by NOVA Science Publishers, USA), 2011, Chapter 6, pp. 193-206.
Approximation capabilities of neural networks with weights from two directions, Azerbaijan Journal of Mathematics 1 (2011), 122-129.
On the proximinality of ridge functions, Sarajevo Journal of Mathematics 5(17) (2009), no. 1, 109-118, http://www.anubih.ba/Journals/vol.5,no-1,y09/12revIsmailov[2].pdf
On the theorem of M Golomb, Proceedings - Mathematical Sciences 119 (2009), no. 1, 45-52, http://dx.doi.org/10.1007/s12044-009-0005-4
On the representation by linear superpositions, Journal of Approximation Theory 151 (2008), Issue 2 , 113-125, http://dx.doi.org/10.1016/j.jat.2007.09.003
On the approximation by weighted ridge functions, Analele Universitatii de Vest din Timisoara, Ser. Math.-Inform. 46 (2008), 75-83.
On the approximation by compositions of fixed multivariate functions with univariate functions, Studia Mathematica 183 (2007), 117-126, http://dx.doi.org/10.4064/sm183-2-2
On the best L₂ approximation by ridge functions, Applied Mathematics E-Notes, 7 (2007), 71-76, http://www.math.nthu.edu.tw/~amen/
Representation of multivariate functions by sums of ridge functions, Journal of Mathematical Analysis and Applications 331 (2007), Issue 1, 184-190, http://dx.doi.org/10.1016/j.jmaa.2006.08.076
Characterization of an extremal sum of ridge functions, Journal of Computational and Applied Mathematics 205 (2007), Issue 1, 105-115, http://dx.doi.org/10.1016/j.cam.2006.04.043
On error formulas for approximation by sums of univariate functions, International Journal of Mathematics and Mathematical Sciences, volume 2006 (2006), Article ID 65620, 11 pages, http://dx.doi.org/10.1155/IJMMS/2006/65620
Methods for computing the least deviation from the sums of functions of one variable, (Russian) Sibirskii Matematicheskii Zhurnal 47 (2006), no. 5, 1076 -1082; translation in Siberian Mathematical Journal 47 (2006), no. 5, 883--888, http://dx.doi.org/10.1007/s11202-006-0097-3
On a theorem of approximation by sums g₁(x₁)+g₂(x₂)+...+g_{n}(x_{n}), Trans. Acad. Sci. Azerb. Ser. Phys.-Tech. Math. Sci. 25 (2005), no. 4, 49-54.
On two-sided exact estimates for the best approximation by sums ϕ(x)+ψ(y) , Trans. Acad. Sci. Azerb. Ser. Phys.-Tech. Math. Sci. 25 (2005), no. 1, 89-94.
On maximization principle of lightning bolts, (Russian) Vestnik of Baku State University 3 (2005), 57-63.
On some classes of bivariate functions characterized by formulas for the best approximation. Radovi Matematicki 13 (2004), 53-62, www.anubih.ba/Journals/vol-13,no-1,y04/07ismailov.pdf
On discontinuity of the best approximation of a continuous function. Trans. Acad. Sci. Azerb. Ser. Phys.-Tech. Math. Sci. 23 (2003), no. 4, 57-60.
On behaviour of the best approximation as a function of an approximation set. Proc. Inst. Math. Mech. Natl. Acad. Sci. Azerb. 19 (2003), 113-116.
Theorem on lightning bolts for elementary domains. Proc. Inst. Math. Mech. Natl. Acad. Sci. Azerb. 17 (2002), 78-85.
On some geometrical conditions for the existence of the best approximating function of the form ϕ(x)+ψ(y). Trans. Acad. Sci. Azerb. Ser. Phys.-Tech. Math. Sci. 19 (1999), no.1-2, 91-95.
On a characteristic property of a family of classes of best approximation. (Russian) Proc. Inst. Math. Mech. Acad. Sci. Azerb. 6 (1997), 74-82.
(with M-B. A. Babaev) Two-sided estimates for the best approximation in domains different from the parallelepiped. Functiones Et Approximatio Commentarii Mathematici 25 (1997), 121-128.
Two-sided estimates for the best approximation in domains consisting of a union of rectangles. (Russian) Izv. Akad. Nauk Azerb. Ser. Fiz-Tekh. Mat. Nauk 17 (1996), no. 1-3, 109-114.
Books
Ridge functions and applications in neural networks. Mathematical Surveys and Monographs, 263. American Mathematical Society, Providence, RI, [2021], ©2021. ix+186 pp. ISBN: 978-1-4704-6765-4 https://bookstore.ams.org/surv-263
Preprints
A note on the equioscillation theorem for best ridge function approximation arXiv:1609.08424
(with R. Aliev) On the representation by bivariate ridge functions arXiv:1606.07940
(with A.Kh. Asgarova) On the Diliberto-Straus algorithm for the uniform approximation by a sum of two algebras arXiv:1603.07073
(with N. Guliyev) A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function arXiv:1601.00013
A note on the representation of continuous functions by linear superpositions arXiv:1501.05277
On the proximinality of ridge functions arXiv:0708.3938
On the theorem of M.Golomb arXiv:0708.3503
On the representation by linear superpositions arXiv:1501.05268
On the approximation by weighted ridge functions arXiv:0708.3356