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

DOI10.1137/21M1437056MaRDI QIDQ5094635zbMATH OpenFDO

Authors 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

deep learningmanifold learninginformation geometryFisher matrix

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• scientific article; zbMATH DE number 1755604
• A manifold learning approach to dimensionality reduction for modeling data
• Data-driven modeling with fuzzy sets and manifolds
• A method for taking models to the data
• On modelling concepts in the conceptual project of data
• scientific article; zbMATH DE number 1944949

Cites work

• scientific article; zbMATH DE number 7306852 (Why is no real title available?)
• Minimizing a differentiable function over a differential manifold
• Natural language processing (almost) from scratch
• Overcoming catastrophic forgetting in neural networks
• Pathological Spectra of the Fisher Information Metric and Its Variants in Deep Neural Networks
• Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment
• Ricci curvature and the manifold learning problem
• Testing the manifold hypothesis

Cited in

(4)

• Deep learning and geometric deep learning: An introduction for mathematicians and physicists
• Model-centric Data Manifold: the Data Through the Eyes of the Model
• Side effects of learning from low-dimensional data embedded in a Euclidean space
• Cartan moving frames and the data manifolds

Describes a project that uses

Uses Software

• AlexNet
• Glow
• ImageNet
• PyTorch

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5094635)