Fundamental Limits of Learning for Generalizability, Data Resilience, and Resource Efficiency
With the advancement of machine learning models and the rapid increase in their range of applications, learning algorithms should not only have the capacity to learn complex tasks, but also be resilient to imperfect data, all while being resource efficient. This thesis explores trade-offs between th...
Main Author: | Blanchard, Moïse |
---|---|
Other Authors: | Jaillet, Patrick |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2024
|
Online Access: | https://hdl.handle.net/1721.1/155479 |
Similar Items
-
A high-generalizability machine learning framework for predicting the progression of Alzheimer’s disease using limited data
by: Caihua Wang, et al.
Published: (2022-04-01) -
Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation
by: Zoey Liu, et al.
Published: (2022-01-01) -
Generalizable and interpretable learning for configuration extrapolation
by: Ding, Yi, et al.
Published: (2022) -
Compositional Robot Learning for Generalizable Interactions
by: Kuo, Yen-Ling
Published: (2022) -
Learning generalizable behaviors from demonstration
by: Corban Rivera, et al.
Published: (2022-10-01)