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

Weights

Learned numeric parameters that scale the strength of connections between neurons.

Definition

Weights, together with biases, make up a network's parameters. Their values are randomly initialized and updated during training to minimize loss. Model files distributed as open weights contain these values.

Exam tip

Weights are learned during training; they are parameters, not hyperparameters.

Related terms