Prevalence of neural collapse during the terminal phase of deep learning training

DOI10.1073/pnas.2015509117zbMath1489.68237arXiv2008.08186OpenAlexW3065974826WikidataQ99594088 ScholiaQ99594088MaRDI QIDQ5073172

No author found.

Publication date: 5 May 2022

Published in: Proceedings of the National Academy of Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.08186

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (3)

Neural collapse under cross-entropy loss ⋮ Neural collapse with unconstrained features ⋮ Deep regularization and direct training of the inner layers of neural networks with kernel flows

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Grassmannian frames with applications to coding and communication
• Adversarial noise attacks of deep learning architectures: stability analysis via sparse-modeled signals
• Group Invariant Scattering
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• Multi-Layer Sparse Coding: The Holistic Way
• Reconciling modern machine-learning practice and the classical bias–variance trade-off

This page was built for publication: Prevalence of neural collapse during the terminal phase of deep learning training