NASA NTRS · 19890052299
Non-Lipschitzian dynamics for neural net modelling
Abstract
Failure of the Lipschitz condition in unstable equilibrium points of dynamical systems leads to a multiple-choice response to an initial deterministic input. The evolution of such systems is characterized by a special type of unpredictability measured by unbounded Liapunov exponents. Possible relation of these systems to future neural networks is discussed.
Keep this discovery
Explore connections, maps & timelines
Zak, Michail. 1989-01-01. Non-Lipschitzian dynamics for neural net modelling. https://ntrs.nasa.gov/citations/19890052299
Cite the original work for its findings. Save a collection to share your selection of sources.