MétaCan
← all works

On the difficulty of training Recurrent Neural Networks

2012· preprint· en· 3,804 citations· W1815076433 on OpenAlex· 10.48550/arxiv.1211.5063

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.

Abstract

There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this paper we attempt to improve the understanding of the underlying issues by exploring these problems from an analytical, a geometric and a dynamical systems perspective. Our analysis is used to justify a simple yet effective solution. We propose a gradient norm clipping strategy to deal with exploding gradients and a soft constraint for the vanishing gradients problem. We validate empirically our hypothesis and proposed solutions in the experimental section.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

The record

Venue
arXiv (Cornell University)
Topic
Neural Networks and Applications
Field
Computer Science
Canadian institutions
Université de Montréal
Funders
Keywords
Constraint (computer-aided design)Perspective (graphical)Computer scienceArtificial neural networkSimple (philosophy)Norm (philosophy)Artificial intelligenceGradient descentAlgorithmMathematical optimizationMathematicsGeometryEpistemology
Has abstract in OpenAlex
yes