AI glossary · Machine learning
Hyperparameter
A hyperparameter is a setting chosen before training an AI model, such as how fast it learns or how many layers it has, that shapes how training goes.
In more detail
Unlike parameters, which the model learns, hyperparameters are picked by people. Examples include the learning rate in gradient descent, the number of training passes and the model’s size.
Finding good values usually means training several versions and comparing the results.
Related terms
ParametersParameters are the internal numbers an AI model learns during training. A model’s size, such as “70 billion parameters”, counts them.Gradient descentGradient descent is the method most AI models use to learn: it repeatedly nudges the model’s settings in the direction that reduces its errors.OverfittingOverfitting is when an AI model learns its training examples too closely, including their noise, so it does well on them but poorly on new data.
Browse related tools
AI tools listed on BroUseAI in these categories.
