Tackle Uncertainty

Tackling uncertainty in various domains, from inventory management to medical image analysis and renewable energy integration, is a central theme in current research. This involves developing robust methods to handle noisy data, unpredictable inputs, and model limitations, often employing probabilistic approaches like Bayesian neural networks or metaheuristics such as Differential Evolution, alongside non-probabilistic techniques like interval learning. Current efforts focus on improving prediction accuracy and reliability through ensemble methods, advanced optimization algorithms, and interpretable models that provide insights into uncertainty sources. These advancements have significant implications for enhancing decision-making in diverse fields, leading to more efficient resource allocation, improved diagnostic accuracy, and more stable energy grids.

Papers

November 4, 2024

Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
Ramneet Kaur, Colin Samplawski, Adam D. Cobb, Anirban Roy, Brian Matejek, Manoj Acharya, Daniel Elenius, Alexander M. Berenbeim, John A. Pavlik, Nathaniel D. Bastian, Susmit Jha
Large Language Model Generative AI Uncertainty Quantification Conformal Prediction System Reliability Tackle Uncertainty

August 16, 2024

Navigating Uncertainties in Machine Learning for Structural Dynamics: A Comprehensive Review of Probabilistic and Non-Probabilistic Approaches in Forward and Inverse Problems
Wang-Ji Yan, Lin-Feng Mei, Jiang Mo, Costas Papadimitriou, Ka-Veng Yuen, Michael Beer
Machine Learning Uncertainty Quantification Inverse Problem Uncertainty Aware Structural Dynamic Uncertainty Awareness Non Probabilistic Tackle Uncertainty

September 22, 2023

Multiple Independent DE Optimizations to Tackle Uncertainty and Variability in Demand in Inventory Management
Sarit Maitra, Sukanya Kundu, Vivek Mishra
Differential Evolution Inventory Management Non Pathological Variability Video Game Demand Meta Heuristic Tackle Uncertainty

August 1, 2023

Addressing Uncertainty in Imbalanced Histopathology Image Classification of HER2 Breast Cancer: An interpretable Ensemble Approach with Threshold Filtered Single Instance Evaluation (SIE)
Md Sakib Hossain Shovon, M. F. Mridha, Khan Md Hasib, Sultan Alfarhood, Mejdl Safran, Dunren Che
Breast Cancer Interpretable Ensemble Class Imbalanced Tackle Uncertainty

June 24, 2023

Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching
H. J. Terry Suh, Glen Chou, Hongkai Dai, Lujie Yang, Abhishek Gupta, Russ Tedrake
Offline Reinforcement Learning First Order Planning Pipeline Offline Model Based Optimization Tackle Uncertainty Score Decomposed Diffusion Model

February 27, 2023

Combating Uncertainties in Wind and Distributed PV Energy Sources Using Integrated Reinforcement Learning and Time-Series Forecasting
Arman Ghasemi, Amin Shojaeighadikolaei, Morteza Hashemi
Reinforcement Learning Time Series Forecasting Smart Grid Energy Management DC Microgrid Application Renewable Generation Wind Pressure Tackle Uncertainty

Tackle Uncertainty

Papers

Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI

Navigating Uncertainties in Machine Learning for Structural Dynamics: A Comprehensive Review of Probabilistic and Non-Probabilistic Approaches in Forward and Inverse Problems

Multiple Independent DE Optimizations to Tackle Uncertainty and Variability in Demand in Inventory Management

Addressing Uncertainty in Imbalanced Histopathology Image Classification of HER2 Breast Cancer: An interpretable Ensemble Approach with Threshold Filtered Single Instance Evaluation (SIE)

Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching

Combating Uncertainties in Wind and Distributed PV Energy Sources Using Integrated Reinforcement Learning and Time-Series Forecasting