A recurrent neural network without chaos

Thomas Laurent, James von Brecht

Abstract: We introduce an exceptionally simple gated recurrent neural network (RNN) that achieves performance comparable to well-known gated architectures, such as LSTMs and GRUs, on the word-level language modeling task. We prove that our model has simple, predicable and non-chaotic dynamics. This stands in stark contrast to more standard gated architectures, whose underlying dynamical systems exhibit chaotic behavior.

Conflicts: lmu.edu, csulb.edu

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/a-recurrent-neural-network-without-chaos/code)