Diagonal RNNs in Symbolic Music Modeling


In this paper, we propose a new Recurrent Neural Network (RNN) architecture. The novelty is simple: We use diagonal recurrent matrices instead of full. This results in better test likelihood and faster convergence compared to regular full RNNs in most of our experiments. We show the benefits of using diagonal recurrent matrices with popularly used LSTM andGRU architectures as well as with the vanilla RNN architecture, on four standard symbolic music datasets.

5 Figures and Tables

Cite this paper

@article{Sbakan2017DiagonalRI, title={Diagonal RNNs in Symbolic Music Modeling}, author={Y. Cem S{\"{u}bakan and Paris Smaragdis}, journal={CoRR}, year={2017}, volume={abs/1704.05420} }