A quick look at NAS (Neural Architecture Search)

2020 NAS surveyr A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions

The current research results are as follows:

There’re five type of methods used in architecture search.

1. reinforcement learning (RL),
2. evolutionary algorithm (EA),
3. gradient optimization (GO),
4. random search (RS)
5. sequential model-based optimization (SMBO).

I don’t understand much about NAS. But from above result, Neural Architectures created by machine have bigger number of parameters and lower precision. So using human-designed neural network architecture is still better for now. Hope there will be some big improvement in NAS in the near future.

There’re some other useful link

1. Awesome-NAS
2. PC-DARTS
3. DARTS

End