Abstract
Distributions maximizing \(S_q\) entropies are not rare in Nature. They have been observed in complex systems in diverse fields, including neuroscience. Nonlinear Fokker-Planck dynamics constitutes one of the main mechanisms that can generate \(S_q\)-maximum entropy distributions. In the present work, we investigate a nonlinear Fokker-Planck equation associated with general, continuous, neural network dynamical models for associative memory. These models admit multiple applications in artificial intelligence, and in the study of mind, because memory is central to many, if not all, the processes investigated by psychology and neuroscience. We explore connections between the nonlinear Fokker-Planck treatment of network dynamics, and the nonequilibrium landscape approach to this dynamics discussed in [34]. We show that the nonequilibrium landscape approach leads to fundamental relations between the Liapunov function of the network model, the deterministic equations of motion (phase-space flow) of the network, and the form of the diffusion coefficients appearing in the nonlinear Fokker-Planck equations. This, in turn, leads to an H-theorem involving a free energy-like functional related to the \(S_q\) entropy. To illustrate these results, we apply them to the Cohen-Grossberg family of neural network models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Beggs, J.M., Plenz, D.: Neuronal avalanches in neocortical circuits. J. Neurosci. 23, 11167–11177 (2003). https://doi.org/10.1523/JNEUROSCI.23-35-11167.2003
Brito, S., da Silva, L.R., Tsallis, C.: Role of dimensionality in complex networks. Nature Sci. Rep. 6, 27992.1–27992.8 (2016). https://doi.org/10.1038/srep27992
de Carvalho, L.A.V., Mendes, D.Q., Wedemann, R.S.: Creativity and delusions: the dopaminergic modulation of cortical maps. In: Sloot, P.M.A., Abramson, D., Bogdanov, A.V., Dongarra, J.J., Zomaya, A.Y., Gorbachev, Y.E. (eds.) ICCS 2003. LNCS, vol. 2657, pp. 511–520. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-44860-8_53
Cleeremans, A., Timmermans, B., Pasquali, A.: Consciousness and metarepresentation: a computational sketch. Neural Netw. 20, 1032–1039 (2007). https://doi.org/10.1016/j.neunet.2007.09.011
Cohen, M.A., Grossberg, S.: Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. Syst. Man. Cybern. 13, 815–826 (1983). https://doi.org/10.1109/TSMC.1983.6313075
Czégel, D., Balogh, S., Pollner, P., Palla, G.: Phase space volume scaling of generalized entropies and anomalous diffusion scaling governed by corresponding non-linear Fokker-Planck equations. Sci. Rep. 8, 1883 (2018). https://doi.org/10.1038/s41598-018-20202-w
da Silva, P.C., da Silva, L.R., Lenzi, E.K., Mendes, R.S., Malacarne, L.C.: Anomalous diffusion and anisotropic nonlinear Fokker-Planck equation. Phys. A 342(1), 16–21 (2004). https://doi.org/10.1016/j.physa.2004.04.054
Fang, X., Kruse, K., Lu, T., Wang, J.: Nonequilibrium physics in biology. Rev. Mod. Phys. 91(4), 045004 (2019). https://doi.org/10.1103/RevModPhys.91.045004
Franck, T.D.: Nonlinear Fokker-Planck Equations: Fundamentals and Applications. Springer, Heidelberg (2005). https://doi.org/10.1007/b137680
Hertz, J.A., Krogh, A., Palmer, R.G., (eds.): Introduction to the Theory of Neural Computation. Lecture Notes, vol. 1. Perseus Books, Cambridge (1991)
Hopfield, J.J.: Neurons with graded responses have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. 81, 3088–3092 (1984). https://doi.org/10.1073/pnas.81.10.3088
Kandel, E.: Psychiatry, Psychoanalysis, and the New Biology of Mind. American Psychiatric Publishing Inc., Washington (2005)
Lenzi, E.K., Lenzi, M.K., Ribeiro, H.V., Evangelista, L.R.: Extensions and solutions for nonlinear diffusion equations and random walks. Proc. Roy. Soc. A: Math. Phys. Eng. Sci. 475(2231), 20190432 (2019). https://doi.org/10.1098/rspa.2019.0432
Lotka, A.J.: Elements of Mathematical Biology. Dover, New York (1956)
de Luca, V.T.F., Wedemann, R.S., Plastino, A.R.: Neuronal asymmetries and Fokker-Planck dynamics. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 703–713. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01424-7_69
Martinez, S., Plastino, A.R., Plastino, A.: Nonlinear Fokker-Planck equations and generalized entropies. Phys. A 259(1–2), 183–192 (1998). https://doi.org/10.1016/S0378-4371(98)00277-5
Papa, A.R.R., da Silva, L.: Earthquakes in the brain. Theory Biosci. 116, 321–327 (1997)
Plastino, A.R., Plastino, A.: Non-extensive statistical mechanics and generalized Fokker-Planck equation. Phys. A 222(1), 347–354 (1995). https://doi.org/10.1016/0378-4371(95)00211-1
Ribeiro, M.S., Nobre, F.D., Curado, E.M.F.: Classes of N-dimensional nonlinear Fokker-Planck equations associated to Tsallis entropy. Entropy 13(11), 1928–1944 (2011). https://doi.org/10.3390/e13111928
Siddiqui, M., Wedemann, R.S., Jensen, H.J.: Avalanches and generalized memory associativity in a network model for conscious and unconscious mental functioning. Phys. A 490, 127–138 (2018). https://doi.org/10.1016/j.physa.2017.08.011
Souza, A.M.C., Andrade, R.F.S., Nobre, F.D., Curado, E.M.F.: Thermodynamic framework for compact \(q\)-Gaussian distributions. Phys. A 491, 153–166 (2018). https://doi.org/10.1016/j.physa.2017.09.013
Tagliazucchi, E., Balenzuela, P., Fraiman, D., Chialvo, D.R.: Criticality in large-scale brain fMRI dynamics unveiled by a novel point process analysis. Front. Physiol.|Fractal Physiol. 3, 15 (2012). https://doi.org/10.3389/fphys.2012.00015
Taylor, J.G.: A neural model of the loss of self in schizophrenia. Schizophrenia Bull. 37(6), 1229–1247 (2011). https://doi.org/10.1093/schbul/sbq033
Tirnakli, U., Borges, E.P.: The standard map: From Boltzmann-Gibbs statistics to Tsallis statistics. Nat. Sci. Rep. 6, 23644.1–23644.8 (2016). https://doi.org/10.1038/srep23644
Tsallis, C.: Introduction to Nonextensive Statistical Mechanics, Approaching a Complex World. Springer, New York (2009). https://doi.org/10.1007/978-0-387-85359-8
Tsallis, C., Stariolo, D.A.: Generalized simulated annealing. Phys. A 233, 395–406 (1996). https://doi.org/10.1016/S0378-4371(96)00271-3
Wang, J., Xu, L., Wang, E.: Potential landscape and flux framework of nonequilibrium networks: robustness, dissipation, and coherence of biochemical oscillations. Proc. Nat. Acad. Sci. 105(34), 12271–12276 (2008). https://doi.org/10.1073/pnas.0800579105, https://www.pnas.org/content/105/34/12271
Wedemann, R.S., Donangelo, R., de Carvalho, L.A.V.: Generalized memory associativity in a network model for the neuroses. Chaos 19(1), 015116 (2009). https://doi.org/10.1063/1.3099608
Wedemann, R.S., Plastino, A.R.: Asymmetries in synaptic connections and the nonlinear Fokker-Planck formalism. In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9886, pp. 19–27. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44778-0_3
Wedemann, R.S., Plastino, A.R.: q-maximum entropy distributions and memory neural networks. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) ICANN 2017. LNCS, vol. 10613, pp. 300–308. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68600-4_35
Wedemann, R.S., Plastino, A.R., Tsallis, C.: Curl forces and the nonlinear Fokker-Planck equation. Phys. Rev. E 94(6), 062105 (2016). https://doi.org/10.1103/PhysRevE.94.062105
Wedemann, R.S., de Carvalho, L.A.V.: Some things psychopathologies can tell us about consciousness. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012. LNCS, vol. 7552, pp. 379–386. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33269-2_48
Wedemann, R.S., de Carvalho, L.A.V., Donangelo, R.: Access to symbolization and associativity mechanisms in a model of conscious and unconscious processes. In: Samsonovich, A.V., Jóhannsdóttir, K.R. (eds.) Biologically Inspired Cognitive Architectures 2011, Frontiers in Artificial Intelligence and Applications, vol. 233, pp. 444–449. IOS Press, Amsterdam, Netherlands (2011). https://doi.org/10.3233/978-1-60750-959-2-444
Yan, H., Zhao, L., Hu, L., Wang, X., Wang, E., Wang, J.: Nonequilibrium landscape theory of neural networks. Proc. Nat. Acad. Sci. 110(45), E4185–E4194 (2013). https://doi.org/10.1073/pnas.1310692110
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wedemann, R.S., Plastino, A.R. (2020). Nonlinear, Nonequilibrium Landscape Approach to Neural Network Dynamics. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12397. Springer, Cham. https://doi.org/10.1007/978-3-030-61616-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-61616-8_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61615-1
Online ISBN: 978-3-030-61616-8
eBook Packages: Computer ScienceComputer Science (R0)