Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 5 of 5 for “"Machine Bias"”.
-
Machine Learning, Machine Bias: A Systematic Survey on ML-Based Floor Model Prediction
… disasters. Artificial intelligence (AI) and machine learning (ML) are rapidly evolving fields with increasing capacities, holding potential for use in processing historical data to create more effective flood model predictions. However, with ML models, the risk of bias remains ever prevalent …
-
Understanding the Mechanism of Racial Bias in Predictive Risk Models of Child Welfare
… it will reproduce, or even exacerbate, human bias. This study focuses on understanding one of the causes of machine bias, which is measurement error or target variable bias. In particular, the research investigates whether the use of a proxy variable, which is foster care placement in our …
-
Towards Trustworthy AI: Investigating Bias and Confidence Alignment in Large Language Models
… self-evaluation of confidence and the subtler biases that shape their outputs. In the first part, we introduce the concept of Confidence Probability Alignment to scrutinize how LLMs’ internal confidence, indicated by token probabilities, aligns with the confidence they express when queried …
-
Analysis of protein and tannin contents in sorghum (Sorghum bicolor (L.) Moench) using near infrared reflectance spectroscopy
… The standard error of prediction corrected for machine bias (SEPc) 0. 43%, ratio of range/SEPc (20. 8), and correlation coefficient (r) between the protein content analyzed by the Kjeldahl method and protein content predicted by NIRS was 0.99 (p < 0.01, n = 28) for the 1983/84 crop year; while …
-
Deep Reinforcement Learning for Data-Agnostic Post-Training Debiasing of Black-Box Machine Learning Models
As reliance on Machine Learning systems in real-world decision-making processes grows, ensuring these systems are free of bias against sensitive demographic groups is of increasing importance. Existing techniques for automatically debiasing ML models generally require access to either the models’ …