Keras Tuner - Auto Neural Network Architecture Selection

#datascience #machinelearning #deeplearning

One of the tedious activity when creating a neural network model is to identify right hyperparameter and neural network architecture. Neural Network typically has lot of hyperparameter to tune

Learning rate
Convolution Layers
Hidden Layers
Number of Conv Filters
Hidden Units

If you put all this together there are lot of permutation and combination. This is where keras tuner comes to play.

Keras Tuner is a distributable hyperparameter optimization framework that solves the pain points of performing a hyperparameter search. Keras Tuner makes it easy to define a search space and leverage included algorithms to find the best hyperparameter values. Keras Tuner comes with Bayesian Optimization, Hyperband, and Random Search algorithms built-in, and is also designed to be easy for researchers to extend in order to experiment with new search algorithms