Neurally imprinted stable vector fields

TitleNeurally imprinted stable vector fields
Publication TypeConference Paper
Year of Publication2013
AuthorsLemme A, Neumann K, Reinhart F, Steil JJ
Abstract

We present a novel learning scheme to imprint stable vector fields into Extreme Learning Machines (ELMs). The networks represent movements, where asymptotic stability is incorporated through constraints derived from Lyapunov stability theory. We show that our approach successfully performs stable and smooth point-to-point movements learned from human handwriting movements.