arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.04876cs.LGmath.DSnlin.CDstat.ML
收藏

Lyapunov引导的递归神经网络性能表示

Lyapunov-Guided Representation of Recurrent Neural Network Performance

University of Washington(华盛顿大学)

Ryan Vogt, Yang Zheng, Eli Shlizerman

AI总结:

本研究将RNN视为动力系统,利用Lyapunov谱分析结合自编码器(AeLLE)关联超参数与准确性,实现训练早期预测最终精度,为RNN架构变体提供新解释方法。

摘要:

递归神经网络(RNN)是处理序列和多变量时间序列数据的普遍计算系统。尽管已知几种稳健的RNN架构,但如何将RNN的初始化、架构及其他超参数与给定任务的准确性相关联尚不明确。在本工作中,我们提出将RNN视为动力系统,并通过Lyapunov谱分析(一种专为非线性动力系统设计的方法)将超参数与准确性相关联。鉴于RNN特征超出了现有Lyapunov谱分析的范畴,我们提出利用自编码器及其潜在表示的嵌入(AeLLE)从Lyapunov谱中推断相关特征。我们对多种RNN架构的研究表明,AeLLE成功地将RNN的Lyapunov谱与准确性相关联。此外,AeLLE学习到的潜在表示可泛化至同一任务的新输入,并在RNN训练过程的早期形成。后一特性使得能够预测训练完成时RNN将收敛到的准确性。我们得出结论,通过Lyapunov谱结合AeLLE对RNN进行表示,为组织和解释RNN架构变体提供了一种新方法。

英文摘要:

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 provides a novel method for organization and interpretation of variants of RNN architectures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑