Diagonal RNNs in Symbolic Music Modeling
This is an incremental improvement for symbolic music modeling, offering potential efficiency gains in RNN-based sequence modeling.
The paper tackles the problem of improving recurrent neural networks for symbolic music modeling by proposing diagonal recurrent matrices instead of full matrices, resulting in better test likelihood and faster convergence in most experiments on four standard datasets.
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 and GRU architectures as well as with the vanilla RNN architecture, on four standard symbolic music datasets.