CUED Publications database

The unreasonable effectiveness of the forget gate

Westhuizen, JVD and Lasenby, J The unreasonable effectiveness of the forget gate. (Unpublished)

Full text not available from this repository.

Abstract

Given the success of the gated recurrent unit, a natural question is whether all the gates of the long short-term memory (LSTM) network are necessary. Previous research has shown that the forget gate is one of the most important gates in the LSTM. Here we show that a forget-gate-only version of the LSTM with chrono-initialized biases, not only provides computational savings but outperforms the standard LSTM on multiple benchmark datasets and competes with some of the best contemporary models. Our proposed network, the JANET, achieves accuracies of 99% and 92.5% on the MNIST and pMNIST datasets, outperforming the standard LSTM which yields accuracies of 98.5% and 91%.

Item Type: Article
Uncontrolled Keywords: cs.NE cs.NE cs.LG stat.ML
Subjects: UNSPECIFIED
Divisions: Div F > Signal Processing and Communications
Depositing User: Cron Job
Date Deposited: 02 Aug 2019 16:20
Last Modified: 18 Feb 2021 14:28
DOI: