Long Expressive Memory for Sequence Modeling


METADATA ONLY
Loading...

Date

2022

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

We propose a novel method called Long Expressive Memory (LEM) for learning long-term sequential dependencies. LEM is gradient-based, it can efficiently process sequential tasks with very long-term dependencies, and it is sufficiently expressive to be able to learn complicated input-output maps. To derive LEM, we consider a system of multiscale ordinary differential equations, as well as a suitable time-discretization of this system. For LEM, we derive rigorous bounds to show the mitigation of the exploding and vanishing gradients problem, a well-known challenge for gradient-based recurrent sequential learning methods. We also prove that LEM can approximate a large class of dynamical systems to high accuracy. Our empirical results, ranging from image and time-series classification through dynamical systems prediction to speech recognition and language modeling, demonstrate that LEM outperforms state-of-the-art recurrent neural networks, gated recurrent units, and long short-term memory models.

Publication status

published

Editor

Book title

The Tenth International Conference on Learning Representations (ICLR 2022)

Journal / series

Volume

Pages / Article No.

Publisher

OpenReview

Event

10th International Conference on Learning Representations (ICLR 2022)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03851 - Mishra, Siddhartha / Mishra, Siddhartha check_circle

Notes

Spotlight presentation held on April 27, 2022.

Funding

770880 - Computation and analysis of statistical solutions of fluid flow (EC)

Related publications and datasets

Is new version of: