A.I. Wiki

Hyperparameter

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.

Start a free consultation today

Our AI experts will chat with you and your solutions architect for a 30 min Q&A.

TALK TO A SKYMIND EXPERT