English

Recent Advances in Recurrent Neural Networks

Neural and Evolutionary Computing 2018-02-26 v3

Abstract

Recurrent neural networks (RNNs) are capable of learning features and long term dependencies from sequential and time-series data. The RNNs have a stack of non-linear units where at least one connection between units forms a directed cycle. A well-trained RNN can model any dynamical system; however, training RNNs is mostly plagued by issues in learning long-term dependencies. In this paper, we present a survey on RNNs and several new advances for newcomers and professionals in the field. The fundamentals and recent advances are explained and the research challenges are introduced.

Keywords

Cite

@article{arxiv.1801.01078,
  title  = {Recent Advances in Recurrent Neural Networks},
  author = {Hojjat Salehinejad and Sharan Sankar and Joseph Barfett and Errol Colak and Shahrokh Valaee},
  journal= {arXiv preprint arXiv:1801.01078},
  year   = {2018}
}

Comments

arXiv admin note: text overlap with arXiv:1602.04335

R2 v1 2026-06-22T23:35:39.064Z