Recent Advances in Recurrent Neural Networks
It is an incremental survey paper summarizing existing knowledge for researchers and practitioners in machine learning.
This paper provides a survey of recurrent neural networks (RNNs), explaining their fundamentals and recent advances to address challenges like learning long-term dependencies, aimed at newcomers and professionals in the field.
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.