PROOF
Print ISSN: 2944-9162, E-ISSN: 2732-9941 An Open Access International Journal of Applied Science and Engineering
Volume 6, 2026
Learning the Chaotic Hénon Map with a Multilayer Perceptron: Prediction Accuracy and Dynamical Analysis
Author:
Search Articles
Abstract: This paper investigates the ability of a multilayer perceptron (MLP) to approximate the dynamics of the classical Hénon map. The reference system is analyzed through its fixed points, Jacobian matrix, local stability, phase portrait, bifurcation diagrams, and maximum Lyapunov exponent. The MLP is trained to learn the transition from consecutive states, $$(x_n,y_n)\mapsto(x_{n+1},y_{n+1})$$, using two hidden layers and the Levenberg–Marquardt algorithm. The training results yield a minimum validation mean squared error of $$2.1488\times10^{-10}$$. Model performance is further assessed through free-running trajectories, phase-space representations, residual distributions, parameter-dependent bifurcation diagrams, and Lyapunov-exponent estimates. The results indicate qualitative similarities between the original system and the learned model. However, divergence in iterated trajectories highlights the limitations of one-step prediction accuracy for reproducing long-term behavior in chaotic systems. Parameter-dependent comparisons are interpreted cautiously because the role of the control parameter in the learned model is not fully specified.
Keywords:
Hénon map, chaotic dynamical systems, multilayer perceptron, supervised learning, attractor
reconstruction, bifurcation diagram, Lyapunov exponent, Levenberg--Marquardt
Pages: 46-55
DOI: 10.37394/232020.2026.6.6