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 6 of 6 for “"data attribution"”.
-
Data Attribution: From Classifiers to Generative Models
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and efficacy. That is, computationally tractable methods can …
-
A Data Attribution-Based Approach to Model Diagnosis in LC-MS/MS Structure Prediction
… in real-world settings. Here, we leverage data attribution methods to systematically identify and validate hypotheses about the sources of generalization challenges that hinder current model performance. Our goal is to automatically uncover insights into the failure modes of existing ML …
-
Machine Learning through the Lens of Data
… model behavior or selecting good training data—require us to relate outputs of models back to the training data. The goal of predictive data attribution, the focus of this thesis, is to precisely characterize the resulting model behavior as a function of the training data in order to tackle …
-
Investigation on ImageNet Remaining Errors with TRAK
The Imagenet dataset is an important benchmark and test bed for computer vision models. Two of its most important characteristics are the size and difficulty, which were what motivated the breakthrough deep learning model Alexnet a decade ago. As researches progress and computation power grows, the …
-
USING COLLABORATIVE WORK GROUPS TO IMPROVE TEACHERS USE OF EBPS FOR STUDENTS WITH DISRUPTIVE BEHAVIOR
… served as a forum for learning about the EBPs. Data sources included coding and thematic analysis of initial and final interviews, recording of the collaborative work groups, classroom observations, prebehavior and postbehavior checklists, and a social validity questionnaire. Three main themes …
-
TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE
… rely on spurious correlations in the training data, leading to performance degradation and unreliability when processing inputs under distribution shifts. This thesis systematically studies the robustness to distribution shifts for ML models from a data-centric perspective. First, we closely …