Difference between revisions of "Neural Architecture"

From
Jump to: navigation, search
Line 18: Line 18:
 
* The search strategy defines which strategy is used to find optimal ANN's within the search space.
 
* 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.  [http://en.wikipedia.org/wiki/Neural_architecture_search Neural Architecture Search | Wikipedia]
 
* 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.  [http://en.wikipedia.org/wiki/Neural_architecture_search Neural Architecture Search | Wikipedia]
 +
 +
* [http://en.wikipedia.org/wiki/Neural_architecture_search#NAS_with_Reinforcement_Learning NAS with Reinforcement Learning | Wikipedia]
  
 
<youtube>sROrvtXnT7Q</youtube>
 
<youtube>sROrvtXnT7Q</youtube>

Revision as of 20:47, 22 March 2019

NAS+machine+learning YouTube search... NAS+machine+learning ...Google search

Various approaches to 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