Skip to main content
SpringerLink
Log in

Discontinuous convex contractions and their applications in neural networks

  • Published:
Computational and Applied Mathematics Aims and scope Submit manuscript

Abstract

In this paper, we show that the class of convex contractions of order \(m\in \mathbb {N}\) is strong enough to generate a fixed point but do not force the mapping to be continuous at the fixed point. As a by-product, we provide a new setting to answer an open question posed by Rhoades (Contemp Math 72:233–245, 1988). In recent years, neural network systems with discontinuous activation functions have received intensive research interest and some theoretical fixed point results (Brouwer’s fixed point theorem, Banach fixed point theorem, Kakutani’s fixed point theorem, Krasnoselskii fixed point theorem, etc.,) have been used in the theoretical studies of neural networks. Therefore, possible applications of our theoretical results can contribute to the study of neural networks both in terms of fixed point theory and discontinuity at fixed point.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  • Alghamdi MA, Alnafei SH, Radenovic S, Shahzad N (2011) Fixed point theorems for convex contraction mappings on cone metric spaces. Math Comput Model 54:2020–2026

    MathSciNet  MATH  Google Scholar 

  • Bisht RK, Özgür N (2020) Geometric properties of discontinuous fixed point set of (\(\epsilon -\delta \)) contractions and applications to neural networks. Aequationes Math 94(5):847–863

    MathSciNet  MATH  Google Scholar 

  • Bisht RK, Pant RP (2017) A remark on discontinuity at fixed point. J Math Anal Appl 445:1239–1241

    MathSciNet  MATH  Google Scholar 

  • Bisht RK (2017) A remark on the result of Radu Miculescu and Alexandru Mihail. J Fixed Point Theory Appl 19(4):2437–2439

    MathSciNet  MATH  Google Scholar 

  • Bisht RK, Rakočević V (2018) Generalized Meir–Keeler type contractions and discontinuity at fixed point. Fixed Point Theory 19:57–64

    MathSciNet  MATH  Google Scholar 

  • Boyd DW, Wong JS (1969) On nonlinear contractions. Proc Am Math Soc 20:458–464

    MathSciNet  MATH  Google Scholar 

  • Cai X, Huang J, Huang L (2018) Periodic orbit analysis for the delayed Filippov system. Proc Am Math Soc 146(11):4667–4682

    MathSciNet  MATH  Google Scholar 

  • Calin O (2020) Activation functions. In: Deep learning architectures. Springer Series in the Data Sciences. Springer, Cham. https://doi.org/10.1007/978-3-030-36721-3_2

  • Du Y, Xu R (2015) Multistability and multiperiodicity for a class of Cohen–Grossberg BAM neural networks with discontinuous activation functions and time delays. Neural Process Lett 42(2):417–435

    Google Scholar 

  • Du Y, Li Y, Xu R (2013) Multistability and multiperiodicity for a general class of delayed Cohen–Grossberg neural networks with discontinuous activation functions. Discrete Dyn Nat Soc. https://doi.org/10.1155/2013/917835

  • Forti M, Nistri P (2003) Global convergence of neural networks with discontinuous neuron activations. IEEE Trans Circuits Syst I Fundam Theory Appl 50(11):1421–1435

    MathSciNet  MATH  Google Scholar 

  • Georgescu F (2017) IFSs consisting of generalized convex contractions. An St Univ Ovidius Constanta 25(1):77–86

    MathSciNet  MATH  Google Scholar 

  • Ghorbanian V, Rezapour S, Shahzad N (2012) Some ordered fixed point results and the property (P). Comput Math Appl 63:1361–1368

    MathSciNet  MATH  Google Scholar 

  • Huang YJ, Chen SJ, Yang XH, Xiao J (2019a) Coexistence and local Mittag–Leffler stability of fractional-order recurrent neural networks with discontinuous activation functions. Chin Phys B 28(4):040701

    Google Scholar 

  • Huang Y, Yuan X, Long H, Fan X, Cai T (2019b) Multistability of fractional-order recurrent neural networks with discontinuous and nonmonotonic activation functions. IEEE Access 7:116430–116437

    Google Scholar 

  • Huang L, Cai Z, Zhang L, Duan L (2013) Dynamical behaviors for discontinuous and delayed neural networks in the framework of Filippov differential inclusions. Neural Netw 48:180–194

    MATH  Google Scholar 

  • Huang Y, Zhang H, Wang Z (2012) Multistability and multiperiodicity of delayed bidirectional associative memory neural networks with discontinuous activation functions. Appl Math Comput 219(3):899–910

    MathSciNet  MATH  Google Scholar 

  • Hussain N, Salimi P (2015) Fixed points for generalized \(\psi -\) contraction with application to intergral equations. J Nonlinear Convex Anal 16(4):711–729

    MathSciNet  MATH  Google Scholar 

  • Istrǎtescu VI (1981) Fixed point theory: An introduction, Mathematics and Its Applications, vol 7. D. Reidel Publishing Company, Dordrecht, Holland, p xv + 466 pp

    Google Scholar 

  • Istrǎtescu VI (1981) Some fixed point theorems for convex contraction mappings and convex nonexpansive mapping I. Lib Math 1:151–163

    MathSciNet  MATH  Google Scholar 

  • Istrǎtescu VI (1982) Some fixed point theorems for convex contraction mappings and mappings with convex diminishing diameters—I. Ann di Mat 130(1):89–104

    MathSciNet  MATH  Google Scholar 

  • Kong F, Zhu Q, Liang F, Nieto JJ (2019) Robust fixed-time synchronization of discontinuous Cohen–Grossberg neural networks with mixed time delays. Nonlinear Anal Modell Control 24(4):603–625

    MathSciNet  MATH  Google Scholar 

  • Latif A, Sintunavarat W, Ninsri A (2015) Approximate fixed point theorems for partial generalized convex contraction in \(\alpha \)-complete metric spaces. Taiwan J Math 19(1):315–333

    MathSciNet  MATH  Google Scholar 

  • Latif A, Ninsri A, Sintunavarat W (2016) The \((\alpha,\beta )\)-generalized convex contractive condition with approximate fixed point results and some consequence. Fixed Point Theory Appl 2016:58. https://doi.org/10.1186/s13663-016-0546-z

    Article  MathSciNet  MATH  Google Scholar 

  • Liu M, Wu H, Zhao W (2020) Event-triggered stochastic synchronization in finite time for delayed semi-Markovian jump neural networks with discontinuous activations. Comput Appl Math 39:1–47

    MathSciNet  MATH  Google Scholar 

  • Liu X, Park JH, Jiang N, Cao J (2014) Nonsmooth finite-time stabilization of neural networks with discontinuous activations. Neural Netw 52:25–32

    MATH  Google Scholar 

  • Matkowski J (1975) Integrable solutions of functional equations. Diss Math 127:1–68

    MathSciNet  MATH  Google Scholar 

  • Miandaragh MA, Postolache M, Rezapour S (2013) Approximate fixed points of generalized convex contractions. Fixed Point Theory Appl 2013:255 8 pp

    MathSciNet  MATH  Google Scholar 

  • Miculescu R, Mihail A (2017) A generalization of Matkowski’s fixed point theorem and Istrǎtescu’s fixed point theorem concerning convex contractions. J Fixed Point Theory Appl 19(2):1525–1533

    MathSciNet  MATH  Google Scholar 

  • Mureşan V, Mureşan AS (2015) On the theory of fixed point theorems for convex contraction mappings. Carpath J Math 31(3):365–371

    MathSciNet  MATH  Google Scholar 

  • Nie X, Cao J (2012) Existence and global stability of equilibrium point for delayed competitive neural networks with discontinuous activation functions. Int J Syst Sci 43(3):459–474

    MathSciNet  MATH  Google Scholar 

  • Nie X, Zheng W X (2014) On multistability of competitive neural networks with discontinuous activation functions. In: Proceedings of the 4th Australian Control Conference (Aucc2014), 17th-18th November, 2014, Canberra, Australia, pp 245–250. https://doi.org/10.1109/AUCC.2014.7358690

  • Nie X, Cao J, Fei S (2019a) Multistability and instability of competitive neural networks with non-monotonic piecewise linear activation functions. Nonlinear Anal Real World Appl 45:799–821

    MathSciNet  MATH  Google Scholar 

  • Nie X, Liang J, Cao J (2019b) Multistability analysis of competitive neural networks with Gaussian-wavelet-type activation functions and unbounded time-varying delays. Appl Math Comput 356:449–468

    MathSciNet  MATH  Google Scholar 

  • Pant RP (1999) Discontinuity and fixed points. J Math Anal Appl 240:284–289

    MathSciNet  MATH  Google Scholar 

  • Pant RP, Özgür NY, Taş N (2020) On discontinuity problem at fixed point. Bull Malays Math Sci Soc 43(1):499–517

    MathSciNet  MATH  Google Scholar 

  • Pant RP, Özgür NY, Taş N (2019) Discontinuity at fixed points with applications. Bull Belg Math Soc Simon Stevin 25(4):571–589

    MathSciNet  MATH  Google Scholar 

  • Pant A, Pant RP (2017) Fixed points and continuity of contractive maps. Filomat 31(11):3501–3506

    MathSciNet  Google Scholar 

  • Rakotch E (1962) A note on contraction mappings. Proc Am Math Soc 13:459–465

    MathSciNet  MATH  Google Scholar 

  • Rhoades BE (1988) Contractive definitions and continuity. Contemp Math 72:233–245

    MathSciNet  MATH  Google Scholar 

  • Rus IA (2016) Some variants of contraction principle, generalizations and applications. Stud Univ Babes Bolyai Math 61(3):343–358

    MathSciNet  MATH  Google Scholar 

  • Rus IA (2001) Generalized contractions and applications. Cluj University Press, Cluj-Napoca

    MATH  Google Scholar 

  • Sastry KPR, Rao CS, Sekhar AC, Balaiah M (2012) Fixed point theorem for cone convex contractions of order \(m\ge 2\). Int J Math Sci Eng Appl 6(1):263–271

    MathSciNet  Google Scholar 

  • Sharma S, Sharma S, Athaiya A (2020) Activation functions in neural networks. Int J Eng Appl Sci Technol 4(12):310–316

    Google Scholar 

  • Wang Z, Huang L, Zuo Y, Zhang L (2010) Global robust stability of time-delay systems with discontinuous activation functions under polytopic parameter uncertainties. Bull Korean Math Soc 47(1):89–102

    MathSciNet  MATH  Google Scholar 

  • Wolfram Research (2019) Inc., Mathematica, Version 12.0, Champaign IL (2019)

  • Zhang H, Wang Z, Liu D (2014) A comprehensive review of stability analysis of continuous-time recurrent neural networks. IEEE Trans Neural Netw Learn Syst 25(7):1229–1262

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics, National Defence Academy, Khadakwasla, Pune, India

    Ravindra K. Bisht

  2. Department of Mathematics, Balıkesir University, 10145, Balıkesir, Turkey

    Nihal Özgür

Authors
  1. Ravindra K. Bisht
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nihal Özgür
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ravindra K. Bisht.

Additional information

Communicated by José Tenreiro Machado.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bisht, R.K., Özgür, N. Discontinuous convex contractions and their applications in neural networks. Comp. Appl. Math. 40, 11 (2021). https://doi.org/10.1007/s40314-020-01390-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s40314-020-01390-6

Keywords

Mathematics Subject Classification

Search

Navigation