Multi-Dimensional Recurrent Neural Networks

Simple item page
dc.creatorGraves, Alex
dc.creatorFernandez, Santiago
dc.creatorSchmidhuber, Juergen
dc.date2007-05-14
dc.date.accessioned2026-07-07T08:01:29Z
dc.date.available2026-07-07T08:01:29Z
dc.descriptionRecurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to input warping, and the ability to access contextual information, are also desirable in multidimensional domains. However, there has so far been no direct way of applying RNNs to data with more than one spatio-temporal dimension. This paper introduces multi-dimensional recurrent neural networks (MDRNNs), thereby extending the potential applicability of RNNs to vision, video processing, medical imaging and many other areas, while avoiding the scaling problems that have plagued other multi-dimensional models. Experimental results are provided for two image segmentation tasks.
dc.description10 pages, 10 figures
dc.identifierhttps://arxiv.org/abs/0705.2011
dc.identifierhttp://arxiv.org/abs/0705.2011
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/128924
dc.subjectArtificial Intelligence
dc.subjectComputer Vision and Pattern Recognition
dc.titleMulti-Dimensional Recurrent Neural Networks
dc.typetext

Files

Collections

arXiv