Bayesian Deep Learning
PulseAugur coverage of Bayesian Deep Learning — every cluster mentioning Bayesian Deep Learning across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New optimizer DP-IVON-Gradsq enhances differential privacy in Bayesian deep learning
Researchers have developed DP-IVON-Gradsq, a new optimizer designed to enhance differential privacy in Bayesian deep learning. This method aims to mitigate the interference between privacy noise and the stochasticity in…
-
New Bayesian Deep Learning Framework Tracks Hardware Impairments in MIMO Receivers
Researchers have developed a novel framework called MP-TTBDL, which utilizes message passing and Bayesian deep learning to jointly track channel and hardware impairments in massive MIMO receivers. This approach models t…
-
New method decomposes AI uncertainty into per-class contributions
Researchers have developed a novel method to decompose epistemic uncertainty in Bayesian deep learning models into per-class contributions. This new metric, termed $C_k(x)$, allows for a more nuanced understanding of mo…
-
AI Model Quantifies London's Air Pollution Regulation Impact
A new study published on arXiv details a Bayesian deep learning framework designed to assess the impact of environmental regulations on air pollution in London. The model, a Bayesian LSTM, integrates various data source…
-
New SIKA-GP Method Accelerates Gaussian Process Inference for Deep Learning
Researchers have developed SIKA-GP, a novel method to accelerate Gaussian Process (GP) inference for Bayesian Deep Learning. By employing sparse inducing kernel approximations with a dyadic ordered template basis, SIKA-…
-
Bayesian deep learning advances with new sampling and inference methods
Two new research papers propose advancements in Bayesian deep learning, focusing on improving inference methods for neural networks. The first paper argues that sampling-based inference (SAI) has reached computational p…
-
Bayesian deep learning evaluation unstable in low-data settings, studies find
Two new arXiv papers highlight significant instability in evaluating Bayesian deep learning methods, particularly under data scarcity. Researchers found that standard evaluation metrics can produce unreliable and datase…