Probabilistic Deep Learning
29 papers with code • 0 benchmarks • 5 datasets
Benchmarks
These leaderboards are used to track progress in Probabilistic Deep Learning
DENSE
VQA-HAT
ADVIO
CBC
Hotel Sales
Latest papers with no code
Interference Motion Removal for Doppler Radar Vital Sign Detection Using Variational Encoder-Decoder Neural Network
A novel approach to the removal of interference through the use of a probabilistic deep learning model is presented.
Informed Spectral Normalized Gaussian Processes for Trajectory Prediction
Previous work has shown that using such informative priors to regularize probabilistic deep learning (DL) models increases their performance and data-efficiency.
Forecasting VIX using Bayesian Deep Learning
Furthermore, we found out that MNF with Gaussian prior outperforms Reparameterization Trick and Flipout models in terms of precision and uncertainty predictions.
Deep Gaussian Mixture Ensembles
This work introduces a novel probabilistic deep learning technique called deep Gaussian mixture ensembles (DGMEs), which enables accurate quantification of both epistemic and aleatoric uncertainty.
Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing
Existing regression models tend to fall short in both accuracy and uncertainty estimation when the label distribution is imbalanced.
Mixture of Experts with Uncertainty Voting for Imbalanced Deep Regression Problems
For regression, recent work relies on the continuity of the distribution; whereas for classification there has been a trend to employ mixture-of-expert models and let some ensemble members specialize in predictions for the sparser regions.
On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study
Modern deep models for summarization attains impressive benchmark performance, but they are prone to generating miscalibrated predictive uncertainty.
Comparison of Probabilistic Deep Learning Methods for Autism Detection
Quantitative methods involving machine learning have been studied and developed to overcome issues with clinical approaches.
Workload Forecasting of a Logistic Node Using Bayesian Neural Networks
Originality: This paper proposes a Bayesian deep learning-based forecasting model for traffic and workload of an empty container depot using real-world data.
A high-resolution canopy height model of the Earth
The worldwide variation in vegetation height is fundamental to the global carbon cycle and central to the functioning of ecosystems and their biodiversity.
