AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

A Bayesian Approach to Recurrence in Neural Networks

Philip N. Garner, Sibo Tong

TPAMI 2020 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Approximate inference in Bayesian neural networks · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use unit-wise Bayesian recurrent unit instead of unidirectional GRUUni-GRU · TIMITphone error rate: p<0.001Improved
use layer-wise BRU instead of bidirectional GRU (no explicit backward pass)Bi-GRU · TIMITphone error rate: p = 0.230No clear effect
make LBRU explicitly bidirectional (Bi-LBRU) versus Bi-GRU and Bi-LSTMBi-GRU · TIMITphone error rate: p=0.43No clear effect
use UBRU or LBRU instead of unidirectional GRUUni-GRU · WSJ eval92word error rate: p=0.19No clear effect
use LBRU instead of bidirectional GRUBi-GRU · WSJ eval92word error rate: p=0.21No clear effect
use layer-wise instead of unit-wise BRUUBRU · AMI-IHMword error rate: p<0.001Improved
make LBRU explicitly bidirectional versus Bi-GRU and Bi-LSTMBi-GRU · AMI-IHMword error rate: p<0.001Improved
use Bi-LSTM (extra gate) instead of Bi-GRUBi-GRU · AMI-IHMword error rateNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy