A.I. Wiki

Interested in AI? Get tips & stories in your inbox:


The term hyperparameter in machine learning is used to distinguish parameters that are not learned from the data used to train a model. In deep learning, hyperparameters include variables used to adjust a neural network such as regularization and learning rate.

Because hyperparameters can be difficult to tune, libraries exist to automatically tune them. Arbiter is one such example.

Interactive Demo

Learn to build AI applications using our interactive learning portal.