Abstract
Machine Learning algorithms are typically regarded as appropriate optimization schemes for minimizing risk functions that are constructed on the training set, which conveys statistical flavor to the corresponding learning problem. When the focus is shifted on perception, which is inherently interwound with time, recent alternative formulations of learning have been proposed that rely on the principle of Least Cognitive Action, which very much reminds us of the Least Action Principle in mechanics. In this paper, we discuss different forms of the cognitive action and show the well-posedness of learning. In particular, unlike the special case of the action in mechanics, where the stationarity is typically gained on saddle points, we prove the existence of the minimum of a special form of cognitive action, which yields forth-order differential equations of learning. We also briefly discuss the dissipative behavior of these equations that turns out to characterize the process of learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Weinberg, S.: The quantum theory of fields. In: Foundations, vol. 1. Cambridge University Press, Cambridge (1995)
Betti, A., Gori, M., Melacci, S.: Cognitive action laws: the case of visual features. In: IEEE Transaction on Neural Networks and Learning Systems (2019). arXiv:cs.CV/1808.09162v1
Betti, A., Gori, M.: The principle of least cognitive action. Theor. Comput. Sci. 633, 83–99 (2016)
Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4, 1–17 (1964)
Su, W., Boyd, S., Candes, E.: A differential equation for modeling Nesterov’s accelerated gradient method: theory and insights. In: Advances in Neural Information Processing Systems, pp. 2510–2518 (2014)
Liero, M., Stefanelli U.: A new minimum principle for Lagrangian mechanics. J. Nonlinear Sci. 23, 179–204 (2013)
Arnold, V.I.: Mathematical methods of classical mechanics. Grad. Texts Math. 60 (1989)
Goldstein, H., Poole, C., Safko, J.: Classical Mechanics. Addison Wesley, Boston (2002)
Suykens, J.A.K: Extending Newton’s law from nonlocal-in-time kinetic energy. Phys. Lett. A 373(14), 1201–1211 (2009)
El-Nabulsi, R.A.: On maximal acceleration and quantum acceleratum operator in quantum mechanics. Quantum Stud. Math. Found. 5(4), 543–550 (2018)
Herrera, L., Nunez, L., Patino, A., Rago, H.: A variational principle and the classical and quantum mechanics of the damped harmonic oscillator. Am. J. Phys. 54(3), 273–277 (1986)
Brezis, H.: Functional Analysis, Sobolev Spaces and Partial Differential Equation. Springer, Berlin (2010)
Acknowledgements
We thank Giovanni Bellettini for having brought to our attention the extended formulation of Newtonian mechanics and for insightful discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Betti, A., Gori, M. (2019). Least Action Principles and Well-Posed Learning Problems. In: Paolucci, M., Sciomachen, A., Uberti, P. (eds) Advances in Optimization and Decision Science for Society, Services and Enterprises. AIRO Springer Series, vol 3. Springer, Cham. https://doi.org/10.1007/978-3-030-34960-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-34960-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34959-2
Online ISBN: 978-3-030-34960-8
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)