Diagonal rnns in symbolic music modeling

By Y. C. Subakan, Paris Smaragdis. 2017

22 citations recorded by the source corpus.

In this paper, we use Diagonal Recurrent Neural Networks on a sequence prediction task. The modification from standard RNN is simple: Diagonal recurrent matrices are used 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling (2018, methodology): “On Nottingham and JSB Chorales, the TCN with virtually no tuning outperforms the recurrent models by a considerable margin, and even outperforms some enhanced recurrent architectures for this task such as HF-RNN (Boulanger-Lewandowski et al., 2012) and Diago-nal RNN (Subakan & Smaragdis, 2017).”
Convolutional Sequence Modeling Revisited (2018, methodology): “…JSB Chorales datasets, the TCN with virtually no tuning is again able to beat the other models by a considerable margin (see Table 1), and even outperforms some improved recurrent models for this task such as HF-RNN (Boulanger-Lewandowski et al., 2012) and Diagonal RNN (Subakan & Smaragdis, 2017).”
Generative Recurrent Networks for De Novo Drug Design (2017, unknown): “RNNs successfully solve machine learning tasks, such as natural language processing([3]) and translation,([4]) and composing music,([5]) to name only a few domains.”