Characterizations of how neural networks learn
Training neural network architectures on Internet-scale datasets has led to many recent advances in machine learning. However, the mechanisms underlying how neural networks learn from data are largely opaque. This thesis develops a mechanistic understanding of how neural networks learn in several se...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2024
|
| Online Access: | https://hdl.handle.net/1721.1/156306 |