Research map / Label-efficient and robust learning / Noisy labels
Modern Neural Networks Generalize on Small Data Sets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| random forest instead of unregularized 10-layer NN | UCI classification · 116 UCI datasets | accuracy: 2.4% | Helped |
| add dropout (keep 0.85) | 10x100 NN · 116 UCI datasets | accuracy | No clear effect |
| ensemble of decorrelated sub-networks vs single sub-network | 10x100 NN · 2D circle simulation | test accuracy: 79%-82% -> 85% | Helped |
Closest papers by meaning
- Regularization for Unsupervised Deep Neural Nets (AAAI 2017 · similarity 0.89)
- Theoretical Limitations of Ensembles in the Age of Overparameterization (ICML 2025 · similarity 0.87)
- United We Stand: Using Epoch-Wise Agreement of Ensembles to Combat Overfit (AAAI 2024 · similarity 0.87)
- Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data (ICLR 2024 · similarity 0.87)
- Rethinking Benign Overfitting in Two-Layer Neural Networks (ICML 2025 · similarity 0.86)
- MaxSup: Overcoming Representation Collapse in Label Smoothing (NeurIPS 2025 · similarity 0.86)
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.