An autoencoder that hard-codes the analytic tent-to-logistic conjugacy in its latent layer learns continuous 1D chaotic maps with lower error and less gradient vanishing than a learned-conjugacy autoencoder, a plain feedforward net, or a PINN.
Controlling nonlinear dynamical sys- tems into arbitrary states using machine learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.DS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
An Improved Autoencoder Conjugacy Network to Learn Chaotic Maps
An autoencoder that hard-codes the analytic tent-to-logistic conjugacy in its latent layer learns continuous 1D chaotic maps with lower error and less gradient vanishing than a learned-conjugacy autoencoder, a plain feedforward net, or a PINN.