Method and apparatus for quantized bayesian deep learning
EP4771538A1Pending Publication Date: 2026-07-08ROBERT BOSCH GMBH +1
Patent Information
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- ROBERT BOSCH GMBH
- Filing Date
- 2023-08-28
- Publication Date
- 2026-07-08
AI Technical Summary
Technical Problem
Deep Neural Networks (DNNs) face challenges in being deployed on low-power devices due to high computational costs, and quantizing parameters to reduce precision leads to decreased performance.
Method used
A stochastic gradient Markov Chain Monte Carlo (SGMCMC) method with approximate Metropolis-Hastings (M-H) corrections is designed for posterior inference of quantized Bayesian neural networks (QBNNs), using a straight-through estimator (STE) and stochastic M-H tests to correct bias caused by discretization.
Benefits of technology
The method achieves superior accuracy compared to baseline SGMCMC and SGD algorithms on various datasets, including UCI, MNIST, CIFAR, and ImageNet, while maintaining efficiency and correcting quantization biases.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN2023115225_06032025_PF_FP_ABST
Abstract
A method for training a quantized Bayesian Neural Network with Monte Carlo (MC) sampling is disclosed. The method comprises initializing a Bayesian Neural Network (BNN) with parameters in an unquantized parameter space, wherein the BNN is used to make an inference with uncertainty based on input images; updating the parameters in the unquantized parameter space during a Metropolis-Hastings (M-H) interval; performing an M-H test to decide whether the updated parameters are acceptable, wherein an accept rate of the M-H test is calculated based on the parameters in the unquantized parameter space; and quantizing the updated parameters into a quantized parameter space with a quantizer.
Need to check novelty before this filing date? Find Prior Art