7
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      LSTM with Working Memory

      Preprint
      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          LSTM is arguably the most successful RNN architecture for many tasks that involve sequential information. In the past few years there have been several proposed improvements to LSTM. We propose an improvement to LSTM which allows communication between memory cells in different blocks and allows an LSTM layer to carry out internal computation within its memory.

          Related collections

          Author and article information

          Journal
          2016-05-06
          2016-05-13
          Article
          1605.01988
          4b5687a7-029d-4fdb-8746-7c1a727661a7

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          Added footnote about initial parameter settings and a few minor corrections/changes
          cs.NE

          Neural & Evolutionary computing
          Neural & Evolutionary computing

          Comments

          Comment on this article