Sorry, you need to enable JavaScript to visit this website.

A Bayesian Interpretation of the Light Gated Recurrent Unit

Citation Author(s):
Alexandre Bittar, Philip N. Garner
Submitted by:
Alexandre Bittar
Last updated:
6 July 2021 - 10:00am
Document Type:
Presentation Slides
Document Year:
2021
Event:
Presenters Name:
Alexandre Bittar
Paper Code:
2242

Abstract 

Abstract: 

We summarise previous work showing that the basic sigmoid activation function arises as an instance of Bayes’s theorem, and that recurrence follows from the prior. We derive a layer- wise recurrence without the assumptions of previous work, and show that it leads to a standard recurrence with modest modifications to reflect use of log-probabilities. The resulting architecture closely resembles the Li-GRU which is the current state of the art for ASR. Although the contribution is mainly theoretical, we show that it is able to outperform the state of the art on the TIMIT and AMI datasets.

up
0 users have voted:

Dataset Files

ICASSP 2021 poster number 2242

(37)