Skip to main content
SpringerLink
Log in

Removing uncertainty in neural networks

  • Research Article
  • Published:
Cognitive Neurodynamics Aims and scope Submit manuscript

Abstract

Neuroscientists draw lines of separation among structures and functions that they judge different, arbitrarily excluding or including issues in our description, to achieve positive demarcations that permits a pragmatic treatment of the nervous activity based on regularity and uniformity. However, uncertainty due to disconnectedness, lack of information and absence of objects’ sharp boundaries is a troubling issue that prevents these scientists to select the required proper sets/subsets during their experimental assessment of natural and artificial neural networks. Starting from the detection of metamorphoses of shapes inside a Euclidean manifold, we propose a technique to detect the topological changes that occur during their reciprocal interactions and shape morphing. This method, that allows the detection of topological holes development and disappearance, makes it possible to solve the problem of uncertainty in the assessment of countless dynamical phenomena, such as cognitive processes, protein homeostasis deterioration, fire propagation, wireless sensor networks, migration flows, and cosmic bodies analysis.

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

Similar content being viewed by others

References

  • Alexandroff P (1961) Elementary concepts of topology. Dover Publications Inc., Ne w York

    Google Scholar 

  • Amad MZ, Peters JF (2018) Maximal centroidal vortices in triangulations. A descriptive proximity framework in analyzing object shapes. Theory Appl Math Comput Sci 8(1):39–59

    Google Scholar 

  • Arkhangelskii AV (2001) [1994]. Extremally-disconnected space. In: Hazewinkel M (eds) Encyclopedia of mathematics. Springer, Berlin. ISBN 978-1-55608-010-4

  • Autrecourt, Nicholas of. About 1340. The Universal Treatise. Marquette University Press, Milwaukee, Wisconsin (1971)

  • Chen J, Quiles-Puchalt N, Chiang YN, Bacigalupe R, Fillol-Salom A et al (2018) Genome hypermobility by lateral transduction. Science 362(6411):207–212. https://doi.org/10.1126/science.aat5867

    Article  CAS  PubMed  Google Scholar 

  • Cooke GE, Finney RL (1967) Homology of cell complexes. Princeton University Press, Princeton

    Book  Google Scholar 

  • Corcoran P, Jones CB (2018) Stability and statistical inferences in the space of topological spatial relationships. IEEE Access 6:18907–18919. https://doi.org/10.1109/ACCESS.2018.2817493

    Article  Google Scholar 

  • Déli E, Tozzi A, Peters JF (2017) Relationships between short and fast brain timescales. Cognit Neurodyn 11(6):539–552

    Article  Google Scholar 

  • Di Concilio A, Guadagni C, Peters JF, Ramanna S (2018) Descriptive proximities. Properties and interplay between classical proximities and overlap. Math Comput Sci 12:91–106. https://doi.org/10.1007/s11786-017-0328-y

    Article  Google Scholar 

  • Edelsbrunner H, Morozov D (2012) Persistent homology: theory and practice. In: European Congress of Mathematics, Krakow, 2–7 July 2012, European Mathematical Society, pp 31–50

  • Edelsbrunner H, Letscher D, Zomorodian A (2002) Topological persistence and simplification. Discrete Comput Geom. https://doi.org/10.1007/s00454-002-2885-2

    Article  Google Scholar 

  • Egenhofer MJ (1991) Reasoning about binary topological relations. In: Symposium on spatial databases. Springer, pp 141–160

  • Fort C (1919). The book of damned. Prometheus Books, 1991

  • Gäuting RH, Bäohlen MH, Erwig M, Lorentzos CSJNA, Schneider M, Vazirgiannis M (2000) A foundation for representing and querying moving objects. ACM Trans Database Syst 25(1):142

    Google Scholar 

  • Ghrist R (2014) Elementary applied topology. Amazon. ISBN 978-1-5028-8085-1

  • Gillam BJ, Grove PM (2011) Contour entropy: a new determinant of perceiving ground or a hole. J Exp Psychol Human Percept Perform 37(3):750–757

    Article  Google Scholar 

  • Harnack D, Pelko M, Chaillet A, Chitour Y, van Rossum MCW (2015) Stability of neuronal networks with homeostatic regulation. PLoS Comput Biol. https://doi.org/10.1371/journal.pcbi.1004357

    Article  PubMed  PubMed Central  Google Scholar 

  • Ignacio PSP, Darcy IK (2019) Tracing patterns and shapes in remittance and migration networks via persistent homology. EPJ Data Sci 8:1. https://doi.org/10.1140/epjds/s13688-018-0179-z

    Article  Google Scholar 

  • Liu H, Schneider M (2011) Tracking continuous topological changes of complex moving regions. In: Proceeding SAC ‘11. Proceedings of the 2011 ACM symposium on applied computing. TaiChung, Taiwan. ACM, New York, NY, USA, pp 833–838. ISBN 978-1-4503-0113-8. https://doi.org/10.1145/1982185.1982366

  • Morimoto RI, Cuervo AM (2009) Protein homeostasis and aging: taking care of proteins from the cradle to the grave. J Gerontol A Biol Sci Med Sci 64A(2):167–170

    Article  CAS  Google Scholar 

  • Overzet LJ, Jung D, Mandra MA, Goeckner M, Dufour T, Dussart R, Lefaucheux P (2010) RF impedance measurements of DC atmospheric micro-discharges. Eur Phys J D 60:449–454. https://doi.org/10.1140/epjd/e2010-00274-5

    Article  Google Scholar 

  • Peters JF (2018a) Proximal planar shapes. Correspondence between triangulated shapes and nerve complexes. Bull Allahabad Math Soc 33:113–137

    Google Scholar 

  • Peters JF (2018b) Proximal vortex cycles and vortex nerve structures. Non-concentric, nesting, possibly overlapping homology cell complexes. J Math Sci Model 1(2):56–72

    Google Scholar 

  • Peters JF (2020) Computational geometry, topology and physics of digital images. Shape complexes, optical vortex nerves and proximities. Springer, Cham. https://doi.org/10.1007/978-3-030-22192-8

    Book  Google Scholar 

  • Popkin RH, Maia Neto JR (eds) (2007) Skepticism: an anthology. Prometheus Books. ISBN 1591024749; ISBN13 9781591024743

  • Pranav P, Edelsbrunner H, van de WeygaertR Vegter G, Kerber M et al (2016) The topology of the cosmic web in terms of persistent Betti numbers. Mon Not R Astron Soc 465(4):4281–4310. https://doi.org/10.1093/mnras/stw2862

    Article  CAS  Google Scholar 

  • Ramstead MJD, Constant A, Badcock PB, Friston KJ (2019) Variational ecology and the physics of sentient systems. Phys Life Rev 31:188–205. https://doi.org/10.1016/j.plrev.2018.12.002

    Article  PubMed  PubMed Central  Google Scholar 

  • Randell DA, Cui Z, Cohn AG (1992) A spatial logic based on regions and connection. In: Proceedings 3rd international conference on knowledge representation and reasoning

  • Rao AR (2018) An oscillatory neural network model that demonstrates the benefits of multisensory learning. Cognit Neurodyn 12(5):481–499

    Article  Google Scholar 

  • Schneider M, Behr T (2006) Topological relationships between complex spatial objects. ACM Trans Database Sys 31(1):39–81

    Article  Google Scholar 

  • Sen S, Daimi SN, Watanabe K, Takahashi K, Bhattacharya J, Saha G (2019) Switch or stay? Automatic classification of internal mental states in bistable perception. Cognit Neurodyn 14:95–113. https://doi.org/10.1007/s11571-019-09548-7

    Article  Google Scholar 

  • Slon V, Mafessoni F, Vernot B, de Filippo C, Grote S et al (2018) The genome of the offspring of a Neanderthal mother and a Denisovan father. Nature 561:113–116

    Article  CAS  Google Scholar 

  • Terasawa J (2004) Extremally disconnected spaces. In: Hart KP, Nagata J, Vaughan JE (eds) Encyclopedia of general topology. Elsevier, Amsterdam. https://doi.org/10.1016/b978-044450355-8/50092-1

    Chapter  Google Scholar 

  • Tozzi A, Peters JF (2017) From abstract topology to real thermodynamic brain activity. Cognit Neurodyn 11(3):283–292

    Article  Google Scholar 

  • Tozzi A, Peters JF (2019) Points and lines inside human brains. Cognit Neurodyn 13(5):417–428

    Article  Google Scholar 

  • Tozzi A, Tor Fla, Peters JF (2016) Building a minimum frustration framework for brain functions in long timescales. J Neurosci Res 94(8):702–716

    Article  CAS  Google Scholar 

  • Verri A, Uras C (1997) Metric-topological approach to shape representation and recognition. Image Vis Comput 14:189–207

    Article  Google Scholar 

  • Verri A, Uras C, Frosini P, Ferri M (1993) On the use of size functions for shape analysis. Biol Cybern 70:99–107

    Article  Google Scholar 

  • Wang P, Hu J (2019) A hybrid model for EEG-based gender recognition. Cognit Neurodyn 13(6):541–554

    Article  Google Scholar 

  • Worboys M (1998) Imprecision in finite resolution spatial data. GeoInformatica 2(3):257–279

    Article  Google Scholar 

  • Worboys M, Duckham M (2006) Monitoring qualitative spatiotemporal change for geosensor networks. Int J Geogr Inf Sci 20:1087–1108

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Center for Nonlinear Science, Department of Physics, University of North Texas, 1155 Union Circle, #311427, Denton, TX, 76203-5017, USA

    Arturo Tozzi

  2. Department of Electrical and Computer Engineering, University of Manitoba, Winnpeg, MB, R3T 5V6, Canada

    James F. Peters

  3. Department of Mathematics, Adıyaman University, 02040, Adıyaman, Turkey

    James F. Peters

Authors
  1. Arturo Tozzi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. James F. Peters
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Arturo Tozzi.

Additional information

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

Tozzi, A., Peters, J.F. Removing uncertainty in neural networks. Cogn Neurodyn 14, 339–345 (2020). https://doi.org/10.1007/s11571-020-09574-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11571-020-09574-w

Keywords

Search

Navigation