Difference between revisions of "Neural Architecture"
m |
|||
| Line 8: | Line 8: | ||
[http://www.google.com/search?q=Neural+Architecture+Search+ NAS+machine+learning ...Google search] | [http://www.google.com/search?q=Neural+Architecture+Search+ NAS+machine+learning ...Google search] | ||
| − | |||
| − | |||
* [[Automated Machine Learning (AML) - AutoML]] | * [[Automated Machine Learning (AML) - AutoML]] | ||
| + | * [[Hyperparameters]] Optimization | ||
* [[Other codeless options, Code Generators, Drag n' Drop]] | * [[Other codeless options, Code Generators, Drag n' Drop]] | ||
* [http://www.engadget.com/2019/03/22/mit-ai-automated-neural-network-design/ MIT’s AI can train neural networks faster than ever before | Christine Fisher - Engadget] | * [http://www.engadget.com/2019/03/22/mit-ai-automated-neural-network-design/ MIT’s AI can train neural networks faster than ever before | Christine Fisher - Engadget] | ||
| + | |||
| + | 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. [http://en.wikipedia.org/wiki/Neural_architecture_search Neural Architecture Search | Wikipedia] | ||
<youtube>sROrvtXnT7Q</youtube> | <youtube>sROrvtXnT7Q</youtube> | ||
Revision as of 20:43, 22 March 2019
NAS+machine+learning YouTube search... NAS+machine+learning ...Google search
- Automated Machine Learning (AML) - AutoML
- Hyperparameters Optimization
- Other codeless options, Code Generators, Drag n' Drop
- MIT’s AI can train neural networks faster than ever before | Christine Fisher - Engadget
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
