AI Paper Atlas

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

Bayesian Layers: A Module for Neural Network Uncertainty

Dustin Tran, Mike Dusenberry, Mark van der Wilk, Danijar Hafner

NeurIPS 2019 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Single-model predictive uncertainty · 77 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
Replace the Transformer’s projection matrices and pointwise feedforward layers with Bayesian layersTransformer · One-Billion-Word Language Modeling Benchmarkperplexity: 23.1No clear effect
Replace fully connected transition-function layers with VariationalDense and add the KL term to the lossPlaNet · cheetah taskscoreNo clear effect
Use Bayesian layers in the TransformerTransformer · WMT14 EN-FRperplexityMixed

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