Difference between revisions of "Neural Architecture"

From
Jump to: navigation, search
(Neural Architecture Search (NAS))
(Neural Architecture Search (NAS))
Line 26: Line 26:
 
* [http://en.wikipedia.org/wiki/Neural_architecture_search#NAS_with_Evolution Neural Architecture Search (NAS) with Evolution | Wikipedia]
 
* [http://en.wikipedia.org/wiki/Neural_architecture_search#NAS_with_Evolution Neural Architecture Search (NAS) with Evolution | Wikipedia]
 
* [http://en.wikipedia.org/wiki/Neural_architecture_search#Multi-objective_Neural_architecture_search Multi-objective Neural architecture search | Wikipedia]
 
* [http://en.wikipedia.org/wiki/Neural_architecture_search#Multi-objective_Neural_architecture_search Multi-objective Neural architecture search | Wikipedia]
 
+
* [http://arxiv.org/abs/1904.09523 Neural Architecture Search for Deep Face Recognition | Ning Zhu]
 +
 
Various approaches to Neural Architecture Search (NAS) have designed networks that are on par or even outperform hand-designed architectures. Methods for NAS can be categorized according to the search space, search strategy and performance estimation strategy used:
 
Various approaches to Neural Architecture Search (NAS) have designed networks that are on par or even outperform hand-designed architectures. Methods for NAS can be categorized according to the search space, search strategy and performance estimation strategy used:
  

Revision as of 23:22, 7 April 2020

YouTube search... ...Google search

Neural Architecture Search (NAS)

YouTube search... ...Google search

Various approaches to Neural Architecture Search (NAS) have designed networks that are on par or even outperform hand-designed architectures. Methods for NAS can be categorized according to the search space, search strategy and performance estimation strategy used:

  • The search space defines which type of ANN can be designed and optimized in principle.
  • The search strategy defines which strategy is used to find optimal ANN's within the search space.
  • Obtaining the performance of an ANN is costly as this requires training the ANN first. Therefore, performance estimation strategies are used obtain less costly estimates of a model's performance. Neural Architecture Search | Wikipedia

Differentiable Neural Computer (DNC)

[YouTube search...]