Abstract
We study a system of ordinary differential equations in \({\mathcal{B}(\mathcal{H})}\) , the space of all bounded linear operators on a separable Hilbert space \({\mathcal{H}}\) . The system considered is a natural generalization of the Oja–Cox–Adams learning models. We establish the local existence of solutions and solve explicitly the system for a class of initial conditions. For such cases, we also characterize the asymptotic behavior of solutions.
Similar content being viewed by others
References
Arrowsmith D. and Place C. (1990). An Introduction to Dynamical Systems. Cambridge University Press, Cambridge
Botelho F. and Jamison J. (2004). Qualitative behavior of differential equations associated with artificial neural networks. J. Dyn. Differ. Equ. 16: 179–204
Botelho F. and Jamison J. (2005). Differential equations in spaces of compact operators. J. Math. Anal. Appl. 308: 105–120
Conway J. (1990). A Course in Functional Analysis, Graduate Texts in Mathematics, vol. 96. Springer, New York
Cox K. and Adams P. (2000). Implications of synaptic digitisation and error for neocortical function. Neurocomputing 32–33: 673–678
Deimling K. (1977). Ordinary Differential Equations in Banach Spaces, Lecture Notes in Mathematics, vol. 596. Springer, New York
Friedman A. (1982). Foundations of Modern Analysis. Dover, Mineola
Haykin S. (1994). Neural Networks: A Comprehensive Foundation. Macmillan College, New York
Hartman P. (1964). Ordinary Differential Equations. Wiley, New York
Mukherjea A. and Pothoven K. (1978). Real and Functional Analysis. Plenum, New York
Oja E. (1982). A simplified neuron model as a principal component analyzer. J. Math. Biol. 15: 267–273
Oja E. and Karhunen J. (1985). A stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix. J. Math. Anal. Appl. 106: 69–84
Pavel N. (1994). Differential Equations, Flow Invariance and Applications, Research Notes in Mathematics, vol. 113. Pitman, London
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Botelho, F., Jamison, J.E. Nonlinear Differential Equations in \({\mathcal{B}(\mathcal{H})}\) Motivated by Learning Models. J Dyn Diff Equat 21, 595–606 (2009). https://doi.org/10.1007/s10884-009-9148-3
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10884-009-9148-3