Publication View

Uniqueness of weights for recurrent nets (1993)

Abstract
We study recurrent neural networks evolving either in discrete or in continuous time. The dynamics of such systems can be described by a set of either difference or differential equations of the following type (to simplify notations, we use the superscripts “+ ” and “. ” to denote time-shift and time-derivative respectively, and we omit the time arguments

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.1001
Source http://www.math.rutgers.edu/~sontag/FTP_DIR/93mtns-nn-extended.pdf
Publisher Akademie Verlag
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Keywords recurrent networks, identifiability, observability
Type text
Language English
Relation 10.1.1.29.6931, 10.1.1.48.3536, 10.1.1.52.1694, 10.1.1.53.4648, 10.1.1.129.3645, 10.1.1.7.6537