Bayesian inference
PulseAugur coverage of Bayesian inference — every cluster mentioning Bayesian inference across labs, papers, and developer communities, ranked by signal.
6 天有情绪数据
-
New Bayesian PINN enhances wheel load estimation for ADAS
Researchers have developed DBPnet, a novel Bayesian physics-informed neural network designed to improve wheel load estimation for advanced driver assistance systems (ADAS). This method incorporates damper characteristic…
-
新方法修正潜高斯模型的贝叶斯推断误差
研究人员开发了一种新方法来修正潜高斯模型的贝叶斯推断误差。提出的重要性采样方案提高了从积分拉普拉斯近似（ILA）得出的近似后验的准确性。这种修正至关重要，因为ILA有时会产生与真实后验显著不同的结果，从而影响后续分析。
-
Bayesian wind tunnels reveal transformer geometric design for inference
Researchers have developed "Bayesian wind tunnels" to rigorously study how transformers perform Bayesian reasoning. These controlled environments allow for the verification of Bayesian posteriors with high accuracy in s…
-
卡尔曼滤波器：AI 的贝叶斯方法在导航与直觉之间的权衡
卡尔曼滤波器是人工智能和机器人学中的一个核心概念，通过一个关于信任 GPS 导航还是个人直觉的问题进行了探讨。这种贝叶斯推理技术对于航空航天导航和控制系统至关重要。
-
New theory models LLM in-context learning as geometric belief space trajectories
Researchers have proposed a new framework for understanding how Large Language Models (LLMs) learn within a given context. Their work suggests that LLMs update their behavior by performing Bayesian inference over a low-…
-
New VPR method improves Bayesian posterior sampling accuracy
Researchers have introduced Variational Predictive Resampling (VPR), a new method designed to improve the accuracy of Bayesian posterior sampling. VPR leverages variational inference's predictive capabilities within a r…
-
New AI framework enhances Bayesian inference with reliable priors
Researchers have developed a new framework to improve Bayesian inference by using AI-generated data to inform prior beliefs. This method, called the rectified AI prior, addresses the risk of propagating errors from pred…
-
表格基础模型适用于贝叶斯推断
研究人员开发了一种名为PFN-NPE的新方法，该方法利用预训练的表格基础模型（特别是TabPFN）作为贝叶斯推断的摘要网络。该方法通过上下文学习来适应这些模型，以处理模拟观测并估计后验分布。虽然PFN-NPE在各种基于模拟的推断场景中都显示出有效性，并且通常能保留关键的后验信息，但在捕捉完整的联合后验结构方面可能存在局限性。
-
New AI research explores advanced methods for uncertainty estimation and Bayesian inference
Researchers have developed a new variational Bayesian framework that directly targets the posterior-predictive distribution, jointly learning approximations for both the posterior and predictive distributions. This appr…
-
New Polynomial Stein Discrepancy method improves Bayesian inference sample quality assessment
Researchers have introduced the Polynomial Stein Discrepancy (PSD), a new method to evaluate the quality of samples generated by Bayesian inference algorithms. This approach aims to overcome the scalability and dimensio…
-
New principle unifies Bayesian inference, game theory, and thermodynamics
A new paper introduces the Game-Theoretic Free Energy Principle, a framework that unifies Bayesian inference, game theory, and thermodynamics. This principle suggests that multi-agent systems minimizing local free energ…
-
New adaptive meta-learning SGHMC algorithm enhances Bayesian updating for structural models
Researchers have developed a new adaptive meta-learning stochastic gradient Hamiltonian Monte Carlo (AM-SGHMC) algorithm designed to improve Bayesian updating of structural dynamic models. This method utilizes adaptive …
-
New VLM framework uses Bayesian inference for efficient expressway anomaly detection
Researchers have developed VIBES, a new framework for detecting anomalies in expressway surveillance videos. VIBES uses Vision-Language Models (VLMs) guided by Bayesian inference to efficiently identify subtle abnormal …
-
GNNs enable Bayesian inversion for discrete structural component states
Researchers have developed a new Bayesian inversion framework using Probabilistic Graphical Models (PGMs) to infer the health states of structural components. This approach addresses challenges in formulating likelihood…