What Makes Freezing Layers in Deep Neural Networks Effective? A Linear Separability Perspective

Collin Coil; Nick Cheney

2025 AutoML AutoML 2025

What Makes Freezing Layers in Deep Neural Networks Effective? A Linear Separability Perspective

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

❓ The Questioner

Authors

Collin Coil, Nick Cheney

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Neural Network Optimization Deep Learning > Architectures > Neural Networks

Keywords

convergence generalization skip connection linear separability over-parameterization freezing layers

Download PDF