Structuring Representations in Deep Learning: Symmetries and Linear Models
The ability of deep neural networks to learn rich data representations is considered paramount to understanding their behavior and empirical success. In particular, imposing known structure on learned representations via careful architecture choice has proven impactful for problems with underlying s...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/147568 |