Neural Expansion: A Unified Mechanism for Deep Neural Network Generalization
In brief
- Neural Expansion explains generalization through the expansion of directionally-selective ray coverage in input space.
- The theory uses Generalization Intervals to measure prediction stability around training samples.
- Empirical results validate the mechanism across diverse architectures and datasets.
A new geometric theory, Neural Expansion, proposes a unified mechanism explaining how deep neural networks generalize despite over-parameterization. It relies on the expansion of directionally-selective ray coverage in input space to quantify prediction stability.
This summary gives you the essentials. The full article, its figures and quotes are on cs.AI updates on arXiv.org.
Read the original articleAI-generated summary of the source, checked by rules. Report an error