Research map / Architectures and efficiency / CNN design
Topological Convolutional Layers for Deep Learning
Ephy R. Love, Benjamin Filippenko, Vasileios Maroulas, Gunnar Carlsson
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 |
|---|---|---|---|
| replace learned first-layer filters with fixed Klein bottle filters and Klein-bottle-sparse connections (TCNN) | 12-layer ResNet · UCF-101 | test accuracy after 100 epochs: 55% -> 70% | Improved |
| use M-F topological first layer instead of learned NOL layer | ResNet trained on KTH · KTH to Weizmann | generalization accuracy: about 52% -> about 65% | Improved |
| use KF + KOL topological layers instead of NOL + NOL | 2-layer CNN · MNIST to SVHN | generalization accuracy: 10% -> 30% | Improved |
| use KF + KOL topological layers instead of NOL + NOL | 2-layer CNN · SVHN to MNIST | generalization accuracy: over 60% accuracy for KF + KOL | Improved |
| add Klein bottle filter layer (KF) with KOL or COL | 2-layer CNN · MNIST, SVHN, USPS trained on 1,000 images | test accuracy | Improved |
| add topological layers under class-correlated Gaussian noise in training or test data | 2-layer CNN · noisy MNIST | test accuracy | Improved |
| use Klein bottle filters instead of an arbitrary Gabor filter family in the fixed filter layer (ablation) | KF + NOL network · 3 digit datasets and 2 cats-dogs datasets | test accuracy | Improved |
| use Klein bottle connectivity in KOL instead of randomly permuted connections with same sparsity (ablation) | KF + KOL · CIFAR-10 | accuracy over training | Improved |
| add a pooling layer (ablation) | CNN and TCNN for digit generalization · MNIST/SVHN generalization | generalization accuracy | No clear effect |
| use TCNN instead of CNN on the simpler KTH dataset | 12-layer ResNet · KTH | test accuracy | Improved |
Closest papers by meaning
- Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework (NeurIPS 2025 · similarity 0.88)
- Learning Connectivity of Neural Networks from a Topological Perspective (ECCV 2020 · similarity 0.88)
- Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity (ICLR 2025 · similarity 0.86)
- TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks (ICML 2025 · similarity 0.85)
- Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves (NeurIPS 2026 · similarity 0.85)
- PICNN: A Pathway towards Interpretable Convolutional Neural Networks (AAAI 2024 · similarity 0.84)
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.
