AI Knowledge HubAI & Models
weight
Weights are numbers expressing how much each connection should count. Training nudges them to shrink the gap between the real answer and the model's mistake, and the tuned numbers themselves become the trained model.
A trained model file contains nothing but these numbers.
Why it mattersThese numbers come up when tracing why a model runs out of capacity or fails to learn a domain. Knowing how weights relate to parameters makes models comparable.
ExampleWeights are numbers expressing how much each connection should count. Training nudges them to shrink the gap between the real answer and the model's mistake, and the tuned numbers themselves become the trained model.