Model-Centric Data Manifold: The Data Through the Eyes of the Model

DOI10.1137/21M1437056MaRDI QIDQ5094635

Luca Grementieri, Rita Fioresi

Publication date: 4 August 2022

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2104.13289

zbMATH Keywords

information geometrymanifold learningFisher matrixdeep learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (1)

Deep learning and geometric deep learning: An introduction for mathematicians and physicists

Uses Software

• PyTorch
• ImageNet
• Glow
• AlexNet

Cites Work

• Minimizing a differentiable function over a differential manifold
• Ricci curvature and the manifold learning problem
• Overcoming catastrophic forgetting in neural networks
• Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment
• Pathological Spectra of the Fisher Information Metric and Its Variants in Deep Neural Networks
• Testing the manifold hypothesis
• Unnamed Item
• Unnamed Item

This page was built for publication: Model-Centric Data Manifold: The Data Through the Eyes of the Model