Relative stability toward diffeomorphisms indicates performance in deep nets*
From MaRDI portal
Recommendations
- Stability for the training of deep neural networks and other classifiers
- Group invariance, stability to deformations, and complexity of deep convolutional representations
- Stable architectures for deep neural networks
- Residual networks as flows of diffeomorphisms
- Forward stability of ResNet and its variants
Cites work
- Breaking the curse of dimensionality with convex neural networks
- Disentangling feature and lazy training in deep neural networks
- Distance-based classification with Lipschitz functions
- Geometric compression of invariant manifolds in neural networks
- Group invariance, stability to deformations, and complexity of deep convolutional representations
- scientific article; zbMATH DE number 921439 (Why is no real title available?)
- Landscape and training regimes in deep learning
- On the information bottleneck theory of deep learning
- Statistical Physics of Fields
- When do neural networks outperform kernel methods?*
- Why do deep convolutional networks generalize so poorly to small image transformations?
Cited in
(2)
This page was built for publication: Relative stability toward diffeomorphisms indicates performance in deep nets*
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5055429)
