Papers › Diagonal RNNs in Symbolic Music Modeling

Diagonal RNNs in Symbolic Music Modeling

18 Apr 2017arXiv:1704.05420archive 2025-07-28

Y. Cem Subakan, Paris Smaragdis

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.

PaperPDFCode

Code

ycemsubakan/diagonal_rnns officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Music Modeling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

GRULSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections