Doctoral Theses: Recent submissions
Now showing items 19-21 of 23400
-
Symmetries in Neural Network Functions and Parameters
(Massachusetts Institute of Technology, 2025-09)Modern neural networks are large, complex objects, which can be difficult to study and work with. In this thesis, I analyze and improve neural networks from the perspective of symmetries, with particular focus on function ... -
Advanced Federated Learning Algorithms Leveraging Selective Forgetting for Data-Constrained Environments
(Massachusetts Institute of Technology, 2025-09)Federated Learning (FL) enables collaborative training of machine learning models without centralizing raw data, offering a practical framework for real-world AI. Yet real-world deployments face challenges in data-constrained ... -
Intuitive but Wrong: Uncovering Student Misconceptions About Force and Motion With Bayesian Item-Response Methods
(Massachusetts Institute of Technology, 2025-09)Students often enter our classrooms with many preexisting beliefs about force and motion learned through a lifetime of hands-on experience. Unfortunately, many of these beliefs are not correct, leading to a wide variety ...
