Research map / Architectures and efficiency / RNNs and normalization
On the Expected Complexity of Maxout Networks
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 maxout-He, Sphere, or Many regions initialization instead of naive He | Deep maxout networks · MNIST | training convergence speed | Helped |
| Increase network depth while keeping the total number of units fixed | Maxout networks at initialization · Networks with n₀ = 2 | number of activation regions | Mixed |
| Use higher-rank maxout units | Maxout networks at initialization · Networks with n₀ = 2 | number of activation regions | Mixed |
Closest papers by meaning
- New Complexity-Theoretic Frontiers of Tractability for Neural Network Training (NeurIPS 2023 · similarity 0.90)
- On the Local Complexity of Linear Regions in Deep ReLU Networks (ICML 2025 · similarity 0.90)
- Exploring the Complexity of Deep Neural Networks through Functional Equivalence (ICML 2024 · similarity 0.87)
- On the Hardness of Training Deep Neural Networks Discretely (AAAI 2025 · similarity 0.87)
- Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training (ICML 2025 · similarity 0.87)
- The Computational Complexity of Counting Linear Regions in ReLU Neural Networks (NeurIPS 2025 · similarity 0.87)
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.