Loading timeline…
20162010s
Neural Architecture Search (NAS)
Using algorithms (like RL or evolutionary methods) to automatically design optimal neural networks.
Why It Was Important
Instead of human engineers guessing the best number of layers and connections, researchers let AIs search the architecture space. This resulted in models like EfficientNet, which radically outperformed human-designed models while using exponentially fewer parameters.
Who Invented It
Quoc Le, Barret Zoph (Google Brain)
Automated ML innovators prioritizing search over intuition.
Applications
- EfficientNet
- AutoML Platforms
- Mobile Model Optimization
Key Papers
- Neural Architecture Search with Reinforcement Learning
Barret Zoph, Quoc V. Le · ICLR 2017 · 2016