Neural Architecture

Jump to: navigation, search

YouTube search... ...Google search

Neural Architecture Search (NAS)

YouTube search... ...Google search

An alternative to manual design is “neural architecture search” (NAS), a series of machine learning techniques that can help discover optimal neural networks for a given problem. Neural architecture search is a big area of research and holds a lot of promise for future applications of deep learning. * Need to find the best AI model for your problem? Try neural architecture search | Ben Dickson - TDW NAS algorithms are efficient problem solvers ... What is neural architecture search (NAS)? | Ben Dickson - TechTalks


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 artificial neural networks (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...]

Neural Operator

YouTube search... ...Google search

A generalization of neural networks to learn operators, termed neural operators, that map between infinite dimensional function spaces. A universal approximator in the function space. the Fourier neural operator model has shown state-of-the-art performance with 1000x speedup in learning turbulent Navier-Stokes equation, as well as promising applications in weather forecast and CO2 migration, as shown in the figure below. Neural Operator Machine learning for scientific computing | Zongy Li