Uncertainty Prediction

Uncertainty prediction in machine learning aims to quantify the reliability of model predictions, addressing the limitations of traditional deterministic models that often output overly confident, yet inaccurate, results. Current research focuses on improving uncertainty estimation through various techniques, including Bayesian neural networks, deep ensembles, and novel architectures like density uncertainty layers and transformer-enhanced networks, often tailored to specific application domains (e.g., medical imaging, autonomous driving). Accurate uncertainty quantification is crucial for building trustworthy AI systems, enabling safer deployment in high-stakes applications and facilitating more informed decision-making across diverse fields.

Papers

November 11, 2024

Predicting Country Instability Using Bayesian Deep Learning and Random Forest
Adam Zebrowski, Haithem Afli
Core Stability Bayesian Deep Learning Forest Environment Random Participation Uncertainty Prediction Global Scale Global Information

October 1, 2024

September 18, 2024

Finetuning Language Models to Emit Linguistic Expressions of Uncertainty
Arslan Chaudhry, Sridhar Thiagarajan, Dilan Gorur
Large Language Model Language Model Question Answering High Uncertainty Anticipation Language Model Fine Tuning Uncertainty Prediction Natural Language Expression Controllable Expression

July 15, 2024

Expert-aware uncertainty estimation for quality control of neural-based blood typing
Ekaterina Zaychenkova, Dmitrii Iarchuk, Sergey Korchagin, Alexey Zaitsev, Egor Ershov
Ground Truth Uncertainty Estimation Uncertainty Prediction Quality Control Accurate Uncertainty Consensus Value

June 23, 2024

Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA
Zehuan Zhang, Hongxiang Fan, Hao Mark Chen, Lukasz Dudziak, Wayne Luk
Field Programmable Gate Array Uncertainty Prediction Dropout Regularization Inference Based Adaptive Dropout Dropout Based

March 25, 2024

EDUE: Expert Disagreement-Guided One-Pass Uncertainty Estimation for Medical Image Segmentation
Kudaibergen Abutalip, Numan Saeed, Ikboljon Sobirov, Vincent Andrearczyk, Adrien Depeursinge, Mohammad Yaqub
Medical Image Segmentation Uncertainty Estimation Expert Knowledge Confidence Calibration Uncertainty Prediction

March 4, 2024

Uncertainty-Aware Prediction and Application in Planning for Autonomous Driving: Definitions, Methods, and Comparison
Wenbo Shao, Jiahui Xu, Zhong Cao, Hong Wang, Jun Li
Autonomous Driving Application Proficiency NCD Method Task Planning Uncertainty Aware Aleatoric Uncertainty Risk Assessment Uncertainty Prediction Autonomous Driving Method

December 31, 2023

Brain Tumor Segmentation Based on Deep Learning, Attention Mechanisms, and Energy-Based Uncertainty Prediction
Zachary Schwehr, Sriman Achanta
Deep Learning Attention Mechanism Magnetic Resonance Imaging Brain Tumor Segmentation Magnetic Resonance Imaging Data Uncertainty Prediction State of the Art Segmentation Brain MR Image

September 1, 2023

Learning-based NLOS Detection and Uncertainty Prediction of GNSS Observations with Transformer-Enhanced LSTM Network
Haoming Zhang, Zhanxin Wang, Heike Vallery
Global Navigation Satellite System Non Line of Sight Uncertainty Prediction

July 4, 2023

Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRI
Xiaojiao Xiao, Qinmin Hu, Guanghui Wang
Uncertainty Prediction Liver Tumor

June 21, 2023

Density Uncertainty Layers for Reliable Uncertainty Estimation
Yookoon Park, David M. Blei
Bayesian Deep Learning Reliable Uncertainty Uncertainty Prediction Density Uncertainty

May 31, 2023

Probabilistic Uncertainty Quantification of Prediction Models with Application to Visual Localization
Junan Chen, Josephine Monica, Wei-Lun Chao, Mark Campbell
Autonomous Driving Application Proficiency Uncertainty Quantification Prediction Model Uncertainty Prediction

May 30, 2023

Taylorformer: Probabilistic Modelling for Random Processes including Time Series
Omer Nivron, Raghul Parthipan, Damon J. Wischik
Time Series Gaussian Process Complex Process Uncertainty Prediction

February 24, 2023

Forecasting Workload in Cloud Computing: Towards Uncertainty-Aware Predictions and Transfer Learning
Andrea Rossi, Andrea Visentin, Diego Carraro, Steven Prestwich, Kenneth N. Brown
Transfer Learning Uncertainty Quantification Cloud Computing Uncertainty Prediction Query Workload Workload Estimation Workload Forecasting

February 10, 2023

Beyond In-Domain Scenarios: Robust Density-Aware Calibration
Christian Tomani, Futa Waseda, Yuesong Shen, Daniel Cremers
Reliable Uncertainty Uncertainty Prediction Post Hoc Calibration

December 14, 2022

Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
Maohao Shen, Yuheng Bu, Prasanna Sattigeri, Soumya Ghosh, Subhro Das, Gregory Wornell
Uncertainty Quantification Uncertainty Prediction Uncertainty Estimation Task Uncertainty Learning

November 4, 2022

Uncertainty-aware predictive modeling for fair data-driven decisions
Patrick Kaiser, Christoph Kern, David Rügamer
Machine Learning Uncertainty Prediction Fair Decision Responsible Machine Learning

October 26, 2022

UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
Yanbo Xu, Alind Khare, Glenn Matlin, Monish Ramadoss, Rishikesan Kamaleswaran, Chao Zhang, Alexey Tumanov
Two Stage Uncertainty Prediction Class Classifier Cost Aware

October 2, 2022

Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective
Michael Dohopolski, Kai Wang, Biling Wang, Ti Bai, Dan Nguyen, David Sher, Steve Jiang, Jing Wang
Deep Learning Model Visual Perspective Uncertainty Estimation Method Uncertainty Prediction Clinical Decision Estimation Method Reliable Prediction Deep Uncertainty

Uncertainty Prediction

Papers

Predicting Country Instability Using Bayesian Deep Learning and Random Forest

Adaptive Motion Generation Using Uncertainty-Driven Foresight Prediction

Revisiting Essential and Nonessential Settings of Evidential Deep Learning

Finetuning Language Models to Emit Linguistic Expressions of Uncertainty

Expert-aware uncertainty estimation for quality control of neural-based blood typing

Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA

EDUE: Expert Disagreement-Guided One-Pass Uncertainty Estimation for Medical Image Segmentation

Uncertainty-Aware Prediction and Application in Planning for Autonomous Driving: Definitions, Methods, and Comparison

Brain Tumor Segmentation Based on Deep Learning, Attention Mechanisms, and Energy-Based Uncertainty Prediction

Learning-based NLOS Detection and Uncertainty Prediction of GNSS Observations with Transformer-Enhanced LSTM Network

Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRI

Density Uncertainty Layers for Reliable Uncertainty Estimation

Probabilistic Uncertainty Quantification of Prediction Models with Application to Visual Localization

Taylorformer: Probabilistic Modelling for Random Processes including Time Series

Forecasting Workload in Cloud Computing: Towards Uncertainty-Aware Predictions and Transfer Learning

Beyond In-Domain Scenarios: Robust Density-Aware Calibration

Post-hoc Uncertainty Learning using a Dirichlet Meta-Model

Uncertainty-aware predictive modeling for fair data-driven decisions

UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification

Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective