Talk
Internal geometry of neural networks
- Patrícia Muñoz Ewald (UCLA)
Abstract
Understanding the internal structure of deep neural networks remains a central challenge in machine learning. In this talk, I will discuss a mathematical tool which reinterprets neural networks as sequences of transformations on a fixed space, enabling a direct comparison of data representations across layers. I will show explicit constructions of classifiers for well-structured data, and emerging structure in networks trained with gradient-based optimizers.
