deephyper.search.nas#

Sub-package for neural architecture search algorithms.

Warning

All search algorithms are MAXIMIZING the objective function. If you want to MINIMIZE the objective function, you have to return the negative of you objective.

Classes

`AMBSMixed`	Asynchronous Model-Based Search baised on the Scikit-Optimized Optimizer.
`AgEBO`	Aging evolution with Bayesian Optimization.
`NeuralArchitectureSearch`
`Random`	Random neural architecture search.
`RegularizedEvolution`	Regularized evolution neural architecture search.
`RegularizedEvolutionMixed`	Extention of the Regularized evolution neural architecture search to the case of joint hyperparameter and neural architecture search.