Network Architecture Search: AutoML and others

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
https://arxiv.org/pdf/1611.01578.pdf

Learning Transferable Architectures for Scalable Image Recognition
https://arxiv.org/pdf/1707.07012.pdf

Progressive Neural Architecture Search
https://arxiv.org/pdf/1712.00559.pdf

Efficient Neural Architecture Search via Parameter Sharing
https://arxiv.org/pdf/1802.03268.pdf

Efficient Architecture Search by Network Transformation
https://arxiv.org/pdf/1707.04873.pdf

Network Morphism
https://arxiv.org/pdf/1603.01670.pdf

Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
https://arxiv.org/pdf/1804.09081.pdf

Auto-Keras: An Efficient Neural Architecture Search System
https://arxiv.org/pdf/1806.10282.pdf

Convolutional Neural Fabrics
https://arxiv.org/pdf/1606.02492.pdf

DARTS: Differentiable Architecture Search
https://arxiv.org/pdf/1806.09055.pdf

Neural Architecture Optimization
https://arxiv.org/pdf/1808.07233.pdf

SMASH: One-Shot Model Architecture Search through HyperNetworks
https://arxiv.org/pdf/1708.05344.pdf

* Off-topic reference
More Parkour Atlas by Boston Dynamics
   • More Parkour Atlas