Weights

Noun · AI & Machine Learning

Definitions

  1. The learned numerical parameters of a neural network, adjusted during training to minimize error. A model's weights are its accumulated knowledge — when someone 'releases model weights,' they're sharing everything the model learned.

    In plain English: The numbers inside an AI model that represent everything it has learned — like the synaptic strengths in a brain, they determine how the model responds to input.

Related Terms