Model-Centric Data Manifold: The Data Through the Eyes of the Model
Authors:
- Luca GrementieriLGLuca Grementieri
- Rita FioresiRita Fioresi
- 28 July 2022
- journal article
- research article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Imaging Sciences
- Vol. 15 (3) , 1140-1156
Abstract
We show that deep ReLU neural network classifiers can see a low-dimensional Riemannian manifold structure on data. Such structure comes via the \sl local data matrix, a variation of the Fisher info...Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Ricci curvature and the manifold learning problemAdvances in Mathematics, 2019
- Feature VisualizationDistill, 2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- Testing the manifold hypothesisJournal of the American Mathematical Society, 2016
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- ImageNet: A large-scale hierarchical image database2009
- Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space AlignmentSIAM Journal on Scientific Computing, 2004
- Natural Gradient Works Efficiently in LearningNeural Computation, 1998
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Minimizing a differentiable function over a differential manifoldJournal of Optimization Theory and Applications, 1982