Thermodynamic limit in learning period three

Abstract

A continuous one-dimensional map with period three includes all periods. This raises the following question: Can we obtain any types of periodic orbits solely by learning three data points? In this paper, we report the answer to be yes. Considering a random neural network in its thermodynamic limit, we first show that almost all learned periods are unstable, and each network has its own characteristic attractors (which can even be untrained ones). The latently acquired dynamics, which are unstable within the trained network, serve as a foundation for the diversity of characteristic attractors and may even lead to the emergence of attractors of all periods after learning. When the neural network interpolation is quadratic, a universal post-learning bifurcation scenario appears, which is consistent with a topological conjugacy between the trained network and the classical logistic map. In addition to universality, we explore specific properties of certain networks, including the singular behavior of the scale of weight at the infinite limit, the finite-size effects, and the symmetry in learning period three.

19 pages, 12 figures

References in corpus (14)

• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Physical reservoir computing -- An introductory perspective
• Attractor Reconstruction by Machine Learning
• Robust Chaos
• Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons
• Embedding and Approximation Theorems for Echo State Networks
• Just Interpolate: Kernel "Ridgeless" Regression Can Generalize
• Anticipating synchronization with machine learning
• Chaos on compact manifolds: Differentiable synchronizations beyond the Takens theorem
• Multifunctionality in a Reservoir Computer
• Learning strange attractors with reservoir systems
• Embedding bifurcations into pneumatic artificial muscle
• Reliability of Neural Networks Based on Spintronic Neurons
• Magic number 7 $\pm$ 2 in networks of threshold dynamics