Gated Orthogonal Recurrent Units: On Learning to Forget

06/08/2017 ∙ by Li Jing, et al. ∙ 0

We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory. We achieve this by extending unitary RNNs with a gating mechanism. Our model is able to outperform LSTMs, GRUs and Unitary RNNs on several long-term dependency benchmark tasks. We empirically both show the orthogonal/unitary RNNs lack the ability to forget and also the ability of GORU to simultaneously remember long term dependencies while forgetting irrelevant information. This plays an important role in recurrent neural networks. We provide competitive results along with an analysis of our model on many natural sequential tasks including the bAbI Question Answering, TIMIT speech spectrum prediction, Penn TreeBank, and synthetic tasks that involve long-term dependencies such as algorithmic, parenthesis, denoising and copying tasks.

READ FULL TEXT

Authors

page 5

Code Repositories

GORU-tensorflow

Gated Orthogonal Recurrent Unit implementation in tensorflow


view repo

URNN-PyTorch

Unitary RNN models implementation in PyTorch: EURNN and GORU


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.