Memory and Information Processing in Recurrent Neural Networks

Abstract

Recurrent neural networks (RNN) are simple dynamical systems whose computational power has been attributed to their short-term memory. Short-term memory of RNNs has been previously studied analytically only for the case of orthogonal networks, and only under annealed approximation, and uncorrelated input. Here for the first time, we present an exact… (More)

Topics

4 Figures and Tables

Cite this paper

@article{Goudarzi2016MemoryAI, title={Memory and Information Processing in Recurrent Neural Networks}, author={Alireza Goudarzi and Sarah Marzen and Peter Banda and Guy Feldman and Christof Teuscher and Darko Stefanovic}, journal={CoRR}, year={2016}, volume={abs/1604.06929} }