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 20 of 108 for “"bias mitigation"”.
-
Modified Loss Functions for Algorithmic Bias Mitigation
… modified loss functions to mitigate race and sex bias caused by data and models. In the first experiment, the trade-off between fairness and accuracy when data is biased and unbiased is explored. A group risk function is introduced and used to create two versions of a modified loss function: Max …
-
Visual bias mitigation driven by Bayesian uncertainties
… datasets reflect our historical and societal biases; in turn, AI learns these correlations during training resulting in predictors and decision-makers exhibiting racism, ableism, sexism and other forms of prejudice. Visual data contains many potential biases given its richness of features, and …
-
Investigating algorithmic bias mitigation in the public sector
… of data practitioners utilising algorithmic bias mitigation methods. This is important because while algorithmic bias mitigation methods have been proposed, little is known about how data practitioners engage with them, nor how practitioners’ perceptions regarding these methods may impact …
-
Expanding Robustness in Responsible AI for Novel Bias Mitigation
… model for a given problem and then apply a bias mitigation strategy. One starts with an existing model architecture and hyperparameters, and then adjusts model weights, learning procedures, or input data to make the model fairer using a pre-, post-, or in-processing bias mitigation …
-
Data-Centric Bias Mitigation in Machine Learning Life Cycle
… of these ML models to inadvertently perpetuate biases, disproportionately impacting certain demographic groups and individuals. For instance, some ML models used in judicial systems have shown biases against African Americans when predicting recidivism rates. Therefore, addressing the inherent …
-
Explainable Bias Mitigation in Transformer-Based Medical Image Analysis
… and trustworthiness. Despite recent advances in bias mitigation techniques, existing approaches primarily focus on convolutional neural networks (CNNs) and rely heavily on retraining or global modifications, which are computationally expensive and lack precision in addressing the root causes of …
-
Integrating Knowledge Into Visual Reasoning: Enhancing Generalizability, Explainability, And Bias Mitigation
… statistically priors. Lastly, the inheritance of bias from various sources are hard to be quantified and alleviated for machine learning models, which is hardly a puzzle for humans. Those critical challenges indicate a core question for AI research: How can existing AI systems evolve a human-like …
-
Advancing Pandemic Response: Integrated Strategies for Testing, Prediction, and Bias Mitigation
… predictive models, and mitigating demographic biases in artificial intelligence (AI) models used for healthcare decision-making. The first study introduces a global screening strategy designed to optimize resource use and increase testing capacity, particularly in low- and middle-income …
-
Security Enhancement and Bias Mitigation for Emerging Sensing and Learning Systems
Artificial intelligence (AI) is being used across various practical tasks in recent years, facilitating many aspects of our daily life. With AI-based sensing and learning systems, we can enjoy the services of automated decision making, computer-assisted medical diagnosis, and health monitoring. …
-
Advanced Image Data Augmentation Strategies to enhance Robustness, Generalization and Bias Mitigation
… approaches often result in feature loss or biased learning. This thesis introduces novel enhancement techniques that address these challenges in multiple domains. First, Random Slices Mixing Data Augmentation (RSMDA) enhances feature diversity by strategically combining image slices while …
-
Model Explanations for Gender and Ethnicity Bias Mitigation in AI-Generated Narratives
… However, their outputs often amplify the biases present in their training data, perpetuating stereotypes and reinforcing societal inequities, particularly regarding gender and ethnicity. Such biases can cause tangible harm, especially for underrepresented groups, and require awareness and …
-
Algorithmic fairness and bias mitigation in clinical machine learning for equitable patient outcomes
… attention, particularly in healthcare where biased algorithms can perpetuate existing disparities. This thesis investigates the role of fairness-aware algorithms in addressing these issues within clinical machine learning applications. Through case studies and empirical analyses, this …
-
Bias Mitigation Strategies for Facial Attribute Classification Leveraging Fine-grained Features and ChatGPT
… research highlights the presence of demographic bias in automated facial attribute classification algorithms, particularly impacting women and individuals with darker skin tones. Existing bias mitigation techniques typically require demographic annotations and often obtain a trade-off between …
-
Evolving Language Patterns on the Web: Community Influence, Model Adaptation, and Bias Mitigation
… on downstream NLP tasks. Second, we explore how biased associations embedded in training data lead to spurious correlations at the concept level. We demonstrate that LLMs tend to internalize these associations, which can skew their predictions and reinforce societal stereotypes. By identifying …
-
School district human resources leadership and bias mitigation in the teacher selection process
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
RESPONSIBLE AI GOVERNANCE: BALANCING THE GOALS OF BIAS MITIGATION AND PRIVACY PROTECTION THROUGH TRANSPARENCY
… focus: the interplay between the goals of debiasing AI systems and safeguarding privacy. While the development and use of AI systems offer significant benefits, they also present serious risks, including data-driven bias that reinforces social inequalities and improper data handling that …
-
Design, Determination, and Evaluation of Gender-Based Bias Mitigation Techniques for Music Recommender Systems
… research that demonstrates presence of gender bias in Machine Learning (ML) models like recommender systems, the issue is viewed as a frivolous cause that doesn’t merit much action. However, gender bias poses to effect more than half of the population as by default ML systems are designed to …
-
GPU ACCELERATED BIAS MITIGATION IN FACE DETECTION USING VARIATIONAL AUTO ENCODERS AND ONNX RUNTIME
Bias in automated face detection—where certain underrepresented groups consistently experience degraded or erroneous inference—remains a significant challenge in computer vision. This thesis proposes an efficient, fairness-aware face detection framework that mitigates bias across both demographic …
-
Investigating user experience and bias mitigation of the multi-modal retrieval of historical data
… artefact data, where the data contains the bias of the curators of the artefacts and there are primary concerns surrounding the social responsibility of these systems. Historians have argued that common information retrieval algorithms may further bias results presented to users. While …
Page 1 of 6