Difference between revisions of "Neural Architecture"
| Line 14: | Line 14: | ||
* [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] | ||
* [[Hierarchical Temporal Memory (HTM)]] | * [[Hierarchical Temporal Memory (HTM)]] | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
= Neural Architecture Search (NAS) = | = Neural Architecture Search (NAS) = | ||
| Line 40: | Line 31: | ||
* 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] | ||
| − | + | <youtube>sROrvtXnT7Q</youtube> | |
| + | <youtube>wL-p5cjDG64</youtube> | ||
| + | <youtube>kn3ae4mg1i8</youtube> | ||
| + | <youtube>mUHHdzPSleQ</youtube> | ||
| + | <youtube>CYUpDogeIL0</youtube> | ||
| + | <youtube>MtuADH7kVeQ</youtube> | ||
Revision as of 22:57, 7 April 2020
YouTube search... ...Google search
- Automated Machine Learning (AML) - AutoML
- Evolutionary Computation / Genetic Algorithms
- Hyperparameters Optimization
- Other codeless options, Code Generators, Drag n' Drop
- MIT’s AI can train neural networks faster than ever before | Christine Fisher - Engadget
- Hierarchical Temporal Memory (HTM)
Neural Architecture Search (NAS)
YouTube search... ...Google search
- Neural Architecture Search (NAS) with Reinforcement Learning | Wikipedia
- Neural Architecture Search (NAS) with Evolution | Wikipedia
- Multi-objective Neural architecture search | Wikipedia
- Awesome NAS; a curated list
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
Differentiable Neural Computer (DNC)
