Research map / Architectures and efficiency / CNN design
Regularization for Unsupervised Deep Neural Nets
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 |
|---|---|---|---|
| Apply partial DropConnect | 3-layer DBN · MNIST | classification error: 1.35% -> 1.30% | Helped |
| Apply partial DropConnect | 3-layer DBM · MNIST | classification error: 1.22% -> 1.12% | Helped |
| Apply partial DropConnect | 2-hidden-layer DBN · NORB | classification error: 11.00% -> 10.81% | Helped |
| Apply Dropout | RSM + logistic regression · 20 Newsgroups | classification error: 30.8% -> 28.8% | Helped |
| Apply partial DropConnect | RSM + logistic regression · 20 Newsgroups | classification error: 30.8% -> 29.7% | Helped |
| Apply partial DropConnect | RSM + logistic regression · Reuters21578 | classification error: 10.50% -> 9.84% | Helped |
| Apply partial DropConnect | Gaussian RBM + FFNN · ISOLET | classification error: 3.98% -> 3.78% | Helped |
| Apply DropConnect | RSM + logistic regression · 20 Newsgroups | classification error: 30.8% -> 35.2% | Hurt |
| Apply partial Dropout instead of Dropout | RSM + logistic regression · Reuters21578 | classification error: 11.91% -> 9.98% | Helped |
| Apply Dropout | 3-layer DBN · MNIST | classification error: 1.35% -> 1.30% | Helped |
Closest papers by meaning
- Modern Neural Networks Generalize on Small Data Sets (NeurIPS 2018 · similarity 0.89)
- Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization (NeurIPS 2017 · similarity 0.88)
- Learning Compact Neural Networks with Regularization (ICML 2018 · similarity 0.86)
- Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel (NeurIPS 2019 · similarity 0.86)
- On Local Overfitting and Forgetting in Deep Neural Networks (AAAI 2025 · similarity 0.84)
- Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers (NeurIPS 2025 · 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.