State Space Representations of Deep Neural Networks

no code implementations • 11 Jun 2018 • Michael Hauser, Sean Gunn, Samer Saab Jr, Asok Ray

This paper deals with neural networks as dynamical systems governed by differential or difference equations.

A Dynamically Controlled Recurrent Neural Network for Modeling Dynamical Systems

no code implementations • 31 Oct 2019 • Yiwei Fu, Samer Saab Jr, Asok Ray, Michael Hauser

This work proposes a novel neural network architecture, called the Dynamically Controlled Recurrent Neural Network (DCRNN), specifically designed to model dynamical systems that are governed by ordinary differential equations (ODEs).