Simple Recurrent Units for Highly Parallelizable Recurrence · HackerPapers discussions

Simple Recurrent Units for Highly Parallelizable Recurrence — mentioned by Smerity

Fri, 04 Oct 2024 01:31:57 GMT

Excited to see more people working on RNNs but wish their citations were better. In 2016 my team from Salesforce Research published our work on the Quasi-Recurrent Neural Network[1] (QRNN). The QRNN variants we describe are near identical (minGRU) or highly similar (minLSTM) to the work here. The QRNN was used, many years ago now, in the first version of Baidu's speech recognition system (Deep Voice [6]) and as part of Google's handwriting recognition system in Gboard[5] (2019). Even if there are expressivity trade-offs when using parallelizable RNNs they've shown historically they can work…

Paper and discussion history. A mention is not an endorsement.

Simple Recurrent Units for Highly Parallelizable Recurrence — HN submission

Tue, 12 Sep 2017 03:01:00 GMT

Training RNNs as Fast as CNNs

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple Recurrent Units for Highly Parallelizable Recurrence — HN submission

Tue, 12 Sep 2017 01:16:26 GMT

Training RNNs as Fast as CNNs

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple Recurrent Units for Highly Parallelizable Recurrence — HN submission

Mon, 11 Sep 2017 09:09:25 GMT

Training RNNs as Fast as CNNs

6 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.