In the Deep Learning Crash Course series, we talked about some of the good practices in designing neural networks but we didn't talk about how to do it automatically. That's what we are going to cover in this video: automatic network architecture search, which is what the media advertises as AI that creates AI.

*** References ***

Neural Architecture Search with Reinforcement Learning
[ Ссылка ]

Learning Transferable Architectures for Scalable Image Recognition
[ Ссылка ]

Progressive Neural Architecture Search
[ Ссылка ]

Efficient Neural Architecture Search via Parameter Sharing
[ Ссылка ]

Efficient Architecture Search by Network Transformation
[ Ссылка ]

Network Morphism
[ Ссылка ]

Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
[ Ссылка ]

Auto-Keras: An Efficient Neural Architecture Search System
[ Ссылка ]

Convolutional Neural Fabrics
[ Ссылка ]

DARTS: Differentiable Architecture Search
[ Ссылка ]

Neural Architecture Optimization
[ Ссылка ]

SMASH: One-Shot Model Architecture Search through HyperNetworks
[ Ссылка ]

* Off-topic reference
More Parkour Atlas by Boston Dynamics
[ Ссылка ]

свернуть