paper-with-me

Papers

Bayesian Layers: A Module for Neural Network Uncertainty

2018-12-10 · NeurIPS 2019 12 · Dustin Tran, Michael W. Dusenberry, Mark van der Wilk, Danijar Hafner

We describe Bayesian Layers, a module designed for fast experimentation with neural network uncertainty. It extends neural network libraries with drop-in replacements for common layers. This enables composition via a unified abstraction over deterministic and stochastic functions and allows for scalability via the underlying system. These layers capture uncertainty over weights (Bayesian neural nets), pre-activation units (dropout), activations ("stochastic output layers"), or the function itself (Gaussian processes). They can also be reversible to propagate uncertainty from input to output. We include code examples for common architectures such as Bayesian LSTMs, deep GPs, and flow-based models. As demonstration, we fit a 5-billion parameter "Bayesian Transformer" on 512 TPUv2 cores for uncertainty in machine translation and a Bayesian dynamics model for model-based planning. Finally, we show how Bayesian Layers can be used within the Edward2 probabilistic programming language for probabilistic programs with stochastic processes.

📄 PDF Abstract BibTeX arXiv:1812.03973

Code (1)

google/edward2 tf

Tasks

Gaussian ProcessesMachine TranslationProbabilistic ProgrammingTranslation

Similar Papers 제목 키워드 기반

The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning

2018-11-29 · Jiaming Zeng, Adam Lesnikowski, Jose M. Alvarez

One of the main challenges of deep learning tools is their inability to capture model uncertainty. While Bayesian deep learning can be used to tackle the problem, Bayesian neural networks often require more time and comp…

Active LearningDeep LearningPosition

Hidden Axis of Uncertainty: Latent-Posterior Alignment in Graph Neural Networks with Bayesian Output Layers

2026-08-21 · Suk Hoon Choi, Damdae Park, Junhyuk Choi, Hyein Jung 외 arxiv

Bayesian Neural Networks (BNNs) with Bayesian output layers provide a principled and tractable framework for quantifying predictive uncertainty, yet the mechanisms shaping that uncertainty remain unclear. While conventio…

Be Bayesian by Attachments to Catch More Uncertainty

2023-10-19 · Shiyu Shen, Bin Pan, Tianyang Shi, Tao Li 외

Bayesian Neural Networks (BNNs) have become one of the promising approaches for uncertainty estimation due to the solid theorical foundations. However, the performance of BNNs is affected by the ability of catching uncer…

Bayesian Neural Networks: Essentials

2021-06-22 · Daniel T. Chang

Bayesian neural networks utilize probabilistic layers that capture uncertainty over weights and activations, and are trained using Bayesian inference. Since these probabilistic layers are designed to be drop-in replaceme…

Bayesian InferenceProbabilistic Deep Learning

Hybrid Bayesian Neural Networks with Functional Probabilistic Layers

2021-07-14 · Daniel T. Chang

Bayesian neural networks provide a direct and natural way to extend standard deep neural networks to support probabilistic deep learning through the use of probabilistic layers that, traditionally, encode weight (and bia…

Bayesian InferenceGaussian ProcessesProbabilistic Deep LearningVariational Inference