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.
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