# Vector Quantized Bayesian Neural Network Inference for Data Streams

arXiv: https://arxiv.org/abs/1907.05911 · HTML: https://mlsanity.com/paper/1907.05911/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [How Do Vision Transformers Work?](https://mlsanity.com/paper/2202.06709/) (2022)
- [Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness](https://mlsanity.com/paper/2105.12639/) (2021)
- [Fast Monte-Carlo Approximation of the Attention Mechanism](https://mlsanity.com/paper/2201.12854/) (2022)
- [Stochastic Weight Sharing for Bayesian Neural Networks](https://mlsanity.com/paper/2505.17856/) (2025)
- [LiDAR Point Cloud Colourisation Using Multi-Camera Fusion and Low-Light Image Enhancement](https://mlsanity.com/paper/2509.25859/) (2025)

## Abstract (arXiv)

Bayesian neural networks (BNN) can estimate the uncertainty in predictions, as opposed to non-Bayesian neural networks (NNs). However, BNNs have been far less widely used than non-Bayesian NNs in practice since they need iterative NN executions to predict a result for one data, and it gives rise to prohibitive computational cost. This computational burden is a critical problem when processing data streams with low-latency. To address this problem, we propose a novel model VQ-BNN, which approximates BNN inference for data streams. In order to reduce the computational burden, VQ-BNN inference predicts NN only once and compensates the result with previously memorized predictions. To be specific, VQ-BNN inference for data streams is given by temporal exponential smoothing of recent predictions. The computational cost of this model is almost the same as that of non-Bayesian NNs. Experiments including semantic segmentation on real-world data show that this model performs significantly faster than BNNs while estimating predictive results comparable to or superior to the results of BNNs.