Research map / Architectures and efficiency / Neural architecture search
Efficient Architecture Search by Network Transformation
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 EAS to search plain CNN architectures through weight-reusing network transformations | Plain CNN architecture search · CIFAR-10+ | test error rate (%): 7.25 -> 4.23 | Helped |
| Use EAS to search plain CNN architectures through weight-reusing network transformations | Plain CNN architecture search · SVHN | test error rate (%): 2.35 -> 1.73 | Helped |
| Use the RL meta-controller instead of random search | EAS architecture search · CIFAR-10+ | search efficiency | Helped |
| Search the DenseNet architecture space with EAS | DenseNet · CIFAR-10 | test error rate (%): 5.19 -> 4.66 | Helped |
| Search the DenseNet architecture space with EAS | DenseNet · CIFAR-10+ | test error rate (%): 3.46 -> 3.44 | Helped |
| Search DenseNet architectures with EAS | DenseNet · CIFAR-10 | parameter count reduction: 43.79% less parameters | Helped |
| Search DenseNet architectures with EAS | DenseNet · CIFAR-10+ | parameter count reduction: 58.20% less parameters | Helped |
Closest papers by meaning
- Path-Level Network Transformation for Efficient Architecture Search (ICML 2018 · similarity 0.91)
- TAPAS: Train-Less Accuracy Predictor for Architecture Search (AAAI 2019 · similarity 0.89)
- Towards modular and programmable architecture search (NeurIPS 2019 · similarity 0.89)
- SMASH: One-Shot Model Architecture Search through HyperNetworks (ICLR 2018 · similarity 0.89)
- Designing Neural Network Architectures using Reinforcement Learning (ICLR 2017 · similarity 0.88)
- Prior Knowledge Guided Neural Architecture Generation (ICML 2025 · similarity 0.88)
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.