Realization theory of recurrent neural networks and rational systems

arXiv1903.05609MaRDI QIDQ6315547FDOQ6315547

Authors: Thibault Defourneau, Mihály Petreczky 

Publication date: 13 March 2019

Abstract: In this paper, we show that, under mild assumptions, input-output behavior of a continous-time recurrent neural network (RNN) can be represented by a rational or polynomial nonlinear system. The assumptions concern the activation function of RNNs, and it is satisfied by many classical activation functions such as the hyperbolic tangent. We also present an algorithm for constructing the polynomial and rational system. This embedding of RNNs into rational systems can be useful for stability, identifiability, and realization theory for RNNs, as these problems have been studied for polynomial/rational systems. In particular, we use this embedding for deriving necessary conditions for realizability of an input-output map by RNN, and for deriving sufficient conditions for minimality of an RNN.

This page was built for publication: Realization theory of recurrent neural networks and rational systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6315547)