thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Foundational

Hyperparameter

A configuration value set before training that controls the learning process, rather than being learned from data.

Definition

Examples include learning rate, batch size, number of epochs, tree depth, number of clusters and regularization strength. In generative AI, inference settings such as temperature and top-p are also sometimes called hyperparameters or inference parameters. Hyperparameters are distinct from model parameters such as weights.

Example

Setting learning_rate=0.001 and batch_size=32 before training.

Exam tip

Weights and biases are parameters (learned); learning rate and epochs are hyperparameters (set).

Related terms