Research map / Architectures and efficiency / CNN design
On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory
Andrea Perin, Stephane Deny
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase the number of rotation angles in the orbit of rotated-MNIST | MLP, ConvNet and ViT-S · rotated-MNIST (leave-out class, out-test) | out-test accuracy | Improved |
| train for very long times (over 1000 epochs) | MLP, ConvNet and ViT-S · rotated-MNIST (leave-out class, out-test) | out-test accuracy | No clear effect |
| use a global average pooling convolutional network instead of a fully connected convolutional network | convolutional network · translated-MNIST (pairs of orbits) | error on left-out point | Improved |
| use non-overlapping filters (stride equals filter size) in the GAP convolutional network (ablation) | GAP convolutional network · rotated-MNIST (pairs of orbits) | orbit classification error | Hurt |
Closest papers by meaning
- Symmetries in Overparametrized Neural Networks: A Mean Field View (NeurIPS 2024 · similarity 0.91)
- Learning symmetries via weight-sharing with doubly stochastic tensors (NeurIPS 2024 · similarity 0.90)
- Learning Infinitesimal Generators of Continuous Symmetries from Data (NeurIPS 2024 · similarity 0.90)
- Improving Equivariant Networks with Probabilistic Symmetry Breaking (ICLR 2025 · similarity 0.90)
- On the hardness of learning under symmetries (ICLR 2024 · similarity 0.89)
- Symmetry Induces Structure and Constraint of Learning (ICML 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
