arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1801.01078cs.NE
收藏

循环神经网络研究进展

Recent Advances in Recurrent Neural Networks

Hojjat Salehinejad, Sharan Sankar, Joseph Barfett, Errol Colak, Shahrokh Valaee

摘要:

循环神经网络(RNN)能够从序列和时间序列数据中学习特征和长期依赖性。RNN具有非线性单元的堆栈,其中单元之间的至少一个连接形成有向循环。经过良好训练的RNN可以对任何动态系统进行建模;然而,训练RNN主要受到学习长期依赖性的问题的困扰。在本文中,我们对RNN进行了调查,并为该领域的新手和专业人士提供了一些新的进展。介绍了该技术的基本原理和最新进展,并介绍了研究面临的挑战。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑