Lyapunov-Guided Representation of Recurrent Neural Network Performance

Author name not available (Why is that?)

Publication date: 11 April 2022

Abstract: Recurrent Neural Networks (RNN) are ubiquitous computing systems for sequences and multivariate time series data. While several robust architectures of RNN are known, it is unclear how to relate RNN initialization, architecture, and other hyperparameters with accuracy for a given task. In this work, we propose to treat RNN as dynamical systems and to correlate hyperparameters with accuracy through Lyapunov spectral analysis, a methodology specifically designed for nonlinear dynamical systems. To address the fact that RNN features go beyond the existing Lyapunov spectral analysis, we propose to infer relevant features from the Lyapunov spectrum with an Autoencoder and an embedding of its latent representation (AeLLE). Our studies of various RNN architectures show that AeLLE successfully correlates RNN Lyapunov spectrum with accuracy. Furthermore, the latent representation learned by AeLLE is generalizable to novel inputs from the same task and is formed early in the process of RNN training. The latter property allows for the prediction of the accuracy to which RNN would converge when training is complete. We conclude that representation of RNN through Lyapunov spectrum along with AeLLE, and assists with hyperparameter selection of RNN, provides a novel method for organization and interpretation of variants of RNN architectures.

Has companion code repository: https://github.com/shlizee/lyapunovautoencode

This page was built for publication: Lyapunov-Guided Representation of Recurrent Neural Network Performance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6396170)