Parameter (machine learning)

The weights and biases that a model learns during training. For example, in a linear regression model, the parameters consist of the bias ($b$) and all the weights ($w_1$, $w_2$, and so on) in the following formula:

$$y' = b + w_1 x_1 + w_2 x_2 + \cdots + w_n x_n$$

In contrast, hyperparameters are the values that you (or a hyperparameter tuning service) supply to the model. For example, learning rate is a hyperparameter.¹

Footnotes

1. developers.google.com/machine-learning/glossary#parameter ↩