Probabilistic Deep Learning

Probabilistic deep learning aims to enhance traditional deep learning models by incorporating uncertainty quantification, enabling more reliable predictions and informed decision-making. Current research focuses on developing and comparing various probabilistic models, including Bayesian neural networks, deep ensembles, and methods leveraging Gaussian processes or mixture models, often applied within architectures like transformers and convolutional neural networks. This field is significant because it addresses the limitations of deterministic deep learning in handling noisy data, out-of-distribution samples, and the need for trustworthy predictions across diverse applications, from autonomous driving to medical diagnosis. Improved uncertainty quantification leads to more robust and reliable AI systems.

Papers

March 18, 2024

Informed Spectral Normalized Gaussian Processes for Trajectory Prediction
Christian Schlauch, Christian Wirth, Nadja Klein
Gaussian Process Trajectory Prediction Prior Knowledge Probabilistic Deep Learning Informative Prior Regularization Based Continual Learning

January 30, 2024

Forecasting VIX using Bayesian Deep Learning
Héctor J. Hortúa, Andrés Mora-Valencia
Temporal Convolutional Network Bayesian Deep Learning Volatility Forecasting Modern Neural Network Probabilistic Deep Learning Volatility Index

October 25, 2023

Stochastic Latent Transformer: Efficient Modelling of Stochastically Forced Zonal Jets
Ira J. S. Shokar, Rich R. Kerswell, Peter H. Haynes
Efficient Model Probabilistic Deep Learning Stochastic Resonance

June 12, 2023

Deep Gaussian Mixture Ensembles
Yousef El-Laham, Niccolò Dalmasso, Elizabeth Fons, Svitlana Vyetrenko
Deep Ensemble Expectation Maximization Gaussian Mixture Probabilistic Deep Learning

June 11, 2023

Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing
Ziyan Wang, Hao Wang
Variational Autoencoders Dynamic Reweighting Probabilistic Deep Learning Imbalanced Regression Node Aware Bi Smoothing Uncertainty Aware Fairness

May 26, 2023

Kernel Density Matrices for Probabilistic Deep Learning
Fabio A. González, Raúl Ramos-Pollán, Joseph A. Gallego-Mejia
Reproducing Kernel Hilbert Space Kernel Matrix Density Matrix Probabilistic Deep Learning

May 24, 2023

Uncertainty Voting Ensemble for Imbalanced Deep Regression
Yuchang Jiang, Vivien Sainte Fare Garnot, Konrad Schindler, Jan Dirk Wegner
Mixture Component Expert Knowledge Mixture of Expert Aleatoric Uncertainty Data Imbalance Probabilistic Deep Learning Imbalanced Regression Regression Loss

April 17, 2023

On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study
Polina Zablotskaia, Du Phan, Joshua Maynez, Shashi Narayan, Jie Ren, Jeremiah Liu
Benchmark Study Generation Task Uncertainty Calibration Low Confidence Probabilistic Deep Learning Neural Summarization

March 9, 2023

Comparison of Probabilistic Deep Learning Methods for Autism Detection
Godfrin Ismail, Kenneth Chesoli, Golda Moni, Kinyua Gikunda
Consistent Comparison Autism Spectrum Disorder Probabilistic Deep Learning

February 2, 2023

Benchmarking Probabilistic Deep Learning Methods for License Plate Recognition
Franziska Schirrmacher, Benedikt Lorch, Anatol Maier, Christian Riess
Uncertainty Quantification License Plate Prediction Uncertainty Recognition Performance Distribution Image Probabilistic Deep Learning

May 31, 2022

FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation
Mehmet Ozgur Turkoglu, Alexander Becker, Hüseyin Anil Gündüz, Mina Rezaei, Bernd Bischl, Rodrigo Caye Daudt, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler
Epistemic Uncertainty Model Ensemble Probabilistic Deep Learning Feature Wise Linear Modulation

May 1, 2022

A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness
Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Zi Lin, Yeming Wen, Ghassen Jerfel, Zack Nado, Jasper Snoek, Dustin Tran, Balaji Lakshminarayanan
Uncertainty Quantification Simple Approach Neural Network Gaussian Process Probabilistic Deep Learning Deep Learning Model Uncertainty

December 5, 2021

Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting
Abdulmajid Murad, Frank Alexander Kraemer, Kerstin Bach, Gavin Taylor
Uncertainty Quantification Predictive Uncertainty Model Uncertainty Air Quality Forecasting Probabilistic Deep Learning State of the Art Uncertainty Deep Probabilistic Forecasting

November 2, 2021

Probabilistic Deep Learning for Real-Time Large Deformation Simulations
Saurabh Deshpande, Jakub Lengiewicz, Stéphane P. A. Bordas
Deep Learning Model Surrogate Model Deep Learning Based Surrogate Probabilistic Deep Learning Force Displacement