Abstract
Recently, Fagerholm, Friston, Moran and Leech advanced a class of linear neural network models complying with Lagrangean dynamics. In the present effort, we explore the possibility of extending the Lagrangean approach to nonlinear models. We present a Lagrangean formalism for a family of nonlinear neural network models, and investigate its main mathematical features.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bateman, H.: On dissipative systems and related variational principles. Phys. Rev. 38(4), 815–819 (1931). https://doi.org/10.1103/PhysRev.38.815
Berto, F., Tagliabue, J., Rossi, G.: There’s plenty of Boole at the bottom: a reversible CA against information entropy. Mind. Mach. 26(4), 341–357 (2016). https://doi.org/10.1007/s11023-016-9401-6
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
Cranford, J.L.: Astrobiological Neurosystems: Rise and Fall of Intelligent Life Forms in the Universe. Springer, Cham (2015)
De Wilde, P.: Class of Hamiltonian neural networks. Phys. Rev. E 47(2), 1392–1396 (1993). https://doi.org/10.1103/PhysRevE.47.1392
Fagerholm, E.D., Friston, K.J., Moran, R.J., Leech, R.: The principle of stationary action in neural systems. arXiv p. 2010.02993 (2020). https://arxiv.org/abs/2010.02993
Feynman, R.P., Leighton, R.B., Sands, M.: The Feynman Lectures on Physics, vol. 2. Addison Wesley, Reading (2006)
Flego, S.P., Frieden, B.R., Plastino, A., Plastino, A.R., Soffer, B.H.: Nonequilibrium thermodynamics and Fisher information: sound wave propagation in a dilute gas. Phys. Rev. E 68(1), 016105 (2003). https://doi.org/10.1103/PhysRevE.68.016105
Friston, K.J., Harrison, L., Penny, W.: Dynamic causal modelling. Neuroimage 19(4), 1273–1302 (2003). https://doi.org/10.1016/S1053-8119(03)00202-7
Goldstein, H.: Classical Mechanics, 2nd edn. Addison-Wesley, New York (1980)
Hertz, J.A., Krogh, A., Palmer, R.G.: Introduction to the Theory of Neural Computation. Lecture Notes, vol. 1. Perseus Books, Cambridge (1991)
Heslot, A.: Quantum mechanics as a classical theory. Phys. Rev. D 31(6), 1341–1348 (1985). https://doi.org/10.1103/PhysRevD.31.1341
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
Kerner, E.H.: A statistical mechanics of interacting biological species. Bull. Math. Biophys. 19, 121–146 (1957)
Kerner, E.H.: Note on Hamiltonian format of Lotka-Volterra dynamics. Phys. Lett. A 151(8), 401–402 (1990). https://doi.org/10.1016/0375-9601(90)90911-7
Lenzi, E.K., de Castro, A.S.M., Mendes, R.S.: Some nonlinear extensions for the Schrödinger equation. Chin. J. Phys. 66, 74–81 (2020). https://doi.org/10.1016/j.cjph.2020.04.019
Lindsay, R.B., Margenau, H.: Foundations of Physics. Dover, New York (1957)
Lotka, A.J.: Elements of Mathematical Biology. Dover, New York (1956)
Mercier, A.: Analytical and Canonical Formalism in Physics. Dover, Mineola (2004)
Morse, M., Feshbach, H.: Methods of Theoretical Physics. McGraw-Hill, New York (1953)
Nowak, M.A.: Evolutionary Dynamics. Harvard University Press, Cambridge (2006)
Plastino, A.R., Plastino, A.: Maximum entropy and approximate descriptions of pure states. Phys. Lett. A 181(6), 446–449 (1993). https://doi.org/10.1016/0375-9601(93)91147-W
Plastino, A.R., Wedemann, R.S.: Nonlinear wave equations related to nonextensive thermostatistics. Entropy 19(2), 60.1–13 (2017). https://doi.org/10.3390/e19020060
Ramond, P.: Field Theory: A Modern Primer. Taylor and Francis, New York (1997)
Rego-Monteiro, M.A., Nobre, F.D.: Nonlinear quantum equations: classical field theory. J. Math. Phys. 54(10), 103302 (2013). https://doi.org/10.1063/1.4824129
Susskind, L., Hrabovsky, G.: The Theoretical Minimum: What You Need to Know to Start Doing Physics. Basic Books, New York (2014)
Wald, R.M.: General Relativity. University of Chicago Press, Chicago (1984)
Wedemann, R.S., Plastino, A.R.: A Nonlinear Fokker-Planck Description of Continuous Neural Network Dynamics. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11727, pp. 43–56. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30487-4_4
Yamano, T.: Gaussian solitary waves for argument-Schrödinger equation. Communications in Nonlinear Science and Numerical Simulation 91, 105449 (2020). https://doi.org/10.1016/j.cnsns.2020.105449
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wedemann, R.S., Plastino, A.R. (2021). Nonlinear Lagrangean Neural Networks. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12894. Springer, Cham. https://doi.org/10.1007/978-3-030-86380-7_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-86380-7_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86379-1
Online ISBN: 978-3-030-86380-7
eBook Packages: Computer ScienceComputer Science (R0)