Research map / Architectures and efficiency / RNNs and normalization
Non-Euclidean Universal Approximation
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 |
|---|---|---|---|
| Use feature and readout maps satisfying the paper's assumptions | Shallow ReLU feed-forward network · California housing test | MAE: 0.320 -> 0.318 | Helped |
| Use feature and readout maps satisfying the paper's assumptions | Shallow ReLU feed-forward network · California housing test | MSE: 0.257 -> 0.247 | Helped |
| Use feature and readout maps satisfying the paper's assumptions | Shallow ReLU feed-forward network · California housing test | MAPE: 17.427 -> 16.714 | Helped |
| Randomize the feature-map network | Shallow ReLU feed-forward network · California housing test | MAE: 0.320 -> 0.320 | No clear effect |
| Randomize the feature-map network | Shallow ReLU feed-forward network · California housing test | MSE: 0.257 -> 0.259 | No clear effect |
| Randomize the feature-map network | Shallow ReLU feed-forward network · California housing test | MAPE: 17.427 -> 17.626 | No clear effect |
| Use feature and readout maps that violate the assumptions | Shallow ReLU feed-forward network · California housing test | MAE: 0.320 -> 0.876 | Hurt |
| Use feature and readout maps that violate the assumptions | Shallow ReLU feed-forward network · California housing test | MSE: 0.257 -> 1.355 | Hurt |
| Use feature and readout maps that violate the assumptions | Shallow ReLU feed-forward network · California housing test | MAPE: 17.427 -> 48.051 | Hurt |
Closest papers by meaning
- Universal approximation power of deep residual neural networks via nonlinear control theory (ICLR 2021 · similarity 0.89)
- A closer look at the approximation capabilities of neural networks (ICLR 2020 · similarity 0.88)
- A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions (NeurIPS 2020 · similarity 0.87)
- Batch normalization is sufficient for universal function approximation in CNNs (ICLR 2024 · similarity 0.87)
- Efficient Deep Approximation of GMMs (NeurIPS 2019 · similarity 0.86)
- Characterizing ResNet's Universal Approximation Capability (ICML 2024 · similarity 0.85)
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.