Abstract

This paper presents analytical results for a class of linear discrete time recurrent neural networks. The networks are shown to be able to act as autoregressive moving average models. Minimal network sizes for representing ARMA(p,q) models are derived, and analogies between recurrent networks and state space models are pointed out.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call