| Paper ID | MLSP-9.1 |
| Paper Title |
A BAYESIAN INTERPRETATION OF THE LIGHT GATED RECURRENT UNIT |
| Authors |
Alexandre Bittar, Philip Garner, Idiap Research Institute, Switzerland |
| Session | MLSP-9: Learning Theory for Neural Networks |
| Location | Gather.Town |
| Session Time: | Tuesday, 08 June, 16:30 - 17:15 |
| Presentation Time: | Tuesday, 08 June, 16:30 - 17:15 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-LEAR] Learning theory and algorithms |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| 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. |
