A Data-Based Perspective on Model Reliability
Neural networks can fail to generalize to real world data — particularly on subpopulations that might have been mislabelled, corrupted, or underrepresented during training. In such settings, the set of features that a model relies on, or its feature prior, often determines the model’s ultimate relia...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2024
|
Online Access: | https://hdl.handle.net/1721.1/153886 |