Uncertainty Aware Model

Uncertainty-aware models aim to improve the reliability and trustworthiness of machine learning predictions by explicitly quantifying and incorporating uncertainty estimates. Current research focuses on developing and applying techniques like Monte Carlo dropout, deep ensembles, and Bayesian neural networks across diverse applications, including image classification, scientific visualization, and process monitoring. This work is crucial for building more robust and reliable AI systems, particularly in high-stakes domains where understanding the confidence of predictions is paramount for informed decision-making. The resulting models offer improved interpretability and facilitate more responsible use of AI in various scientific and practical settings.

Papers

November 14, 2024

Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems
Benjamin Kolicic, Alberto Caron, Chris Hicks, Vasilios Mavroudis
LeArning Abstract Inherent Interpretability Uncertainty Quantification Online Service Security Implication Uncertainty Aware Model Uncertainty Awareness

September 19, 2024

Trust-informed Decision-Making Through An Uncertainty-Aware Stacked Neural Networks Framework: Case Study in COVID-19 Classification
Hassan Gharoun, Mohammad Sadegh Khorshidi, Fang Chen, Amir H. Gandomi
Case Study Uncertainty Aware Diagnosis Prediction Uncertainty Aware Model Trust Aware

July 23, 2024

Uncertainty-Aware Deep Neural Representations for Visual Analysis of Vector Field Data
Atul Kumar, Siddharth Garg, Soumya Dutta
Visual Data Uncertainty Visualization Deep Uncertainty Uncertainty Aware Model

July 17, 2024

Domain-specific or Uncertainty-aware models: Does it really make a difference for biomedical text classification?
Aman Sinha, Timothee Mickus, Marianne Clausel, Mathieu Constant, Xavier Coubez
Language Model Text Classification Domain Specific NLP Community Qualitative Difference Uncertainty Aware Model Uncertainty Awareness Domain Specific Foundation Model Domain Specificity

May 22, 2024

Visual Analysis of Prediction Uncertainty in Neural Networks for Deep Image Synthesis
Soumya Dutta, Faheem Nizar, Ahmad Amaan, Ayan Acharya
Neural Network Image Synthesis Visual Data Prediction Uncertainty Relevant Visualization Uncertainty Visualization Uncertainty Aware Model

October 19, 2023

Model-agnostic variable importance for predictive uncertainty: an entropy-based approach
Danny Wood, Theodore Papamarkou, Matt Benatan, Richard Allmendinger
High Explainability Predictive Uncertainty Variable Importance Predictive Distribution Permutation Importance Entropy Based Conditional Expectation Uncertainty Aware Model

June 26, 2023

Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception
Junwon Seo, Jungwi Mun, Taekyung Kim
External Control High Uncertainty Anticipation Perception Aware State Action Space Unstructured Environment Safe Navigation Autonomous Navigation System Vehicle Dynamic Traversability Prediction Uncertainty Aware Model

March 20, 2023

Uncertainty-aware deep learning for digital twin-driven monitoring: Application to fault detection in power lines
Laya Das, Blazhe Gjorgiev, Giovanni Sansavini
Deep Learning Deep Neural Network Data Detection Digital Twin Uncertainty Aware Prediction Uncertainty Parameter Uncertainty Power Line Deep Neural Network Parameter Uncertainty Aware Model

September 5, 2022

A Robust Learning Methodology for Uncertainty-aware Scientific Machine Learning models
Erbet Costa Almeida, Carine de Menezes Rebello, Marcio Fontana, Leizer Schnitman, Idelfonso Bessa dos Reis Nogueira
Uncertainty Estimation Robust Learning Uncertainty Aware Model Uncertainty Decomposition SciML Model Robust Learning Method

August 2, 2022

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
Mark Penrod, Harrison Termotto, Varshini Reddy, Jiayu Yao, Finale Doshi-Velez, Weiwei Pan
Predictive Uncertainty Financial Success Uncertainty Aware Deep Learning Task Ambiguity Uncertainty Aware Model

June 13, 2022

Learning Uncertainty with Artificial Neural Networks for Improved Predictive Process Monitoring
Hans Weytjens, Jochen De Weerdt
Neural Network Bayesian Neural Network Model Uncertainty Predictive Process Monitoring Uncertainty Aware Model

May 24, 2022

Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs
Çağatay Yıldız, Melih Kandemir, Barbara Rakitsch
Gaussian Process Dynamical System Efficient Inference Sparse Variational Gaussian Process Continuous Time Dynamic Uncertainty Aware Model

Uncertainty Aware Model

Papers

Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems

Trust-informed Decision-Making Through An Uncertainty-Aware Stacked Neural Networks Framework: Case Study in COVID-19 Classification

Uncertainty-Aware Deep Neural Representations for Visual Analysis of Vector Field Data

Domain-specific or Uncertainty-aware models: Does it really make a difference for biomedical text classification?

Visual Analysis of Prediction Uncertainty in Neural Networks for Deep Image Synthesis

Model-agnostic variable importance for predictive uncertainty: an entropy-based approach

Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception

Uncertainty-aware deep learning for digital twin-driven monitoring: Application to fault detection in power lines

A Robust Learning Methodology for Uncertainty-aware Scientific Machine Learning models

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry

Learning Uncertainty with Artificial Neural Networks for Improved Predictive Process Monitoring

Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs