Okuzeka
Artificial Intelligence & Machine Learning vocabulary · Neural Networks and Deep Learning

Weights

Meaning in artificial intelligence & machine learning, with examples

/weɪts/nounCommon term

In artificial intelligence & machine learning, weights means: The learned numbers on the connections of a neural network, which decide how strongly each input affects the next layer. Together they hold what the model has learned.

In Turkish: ağırlıklar

How it is used

Usually plural. Engineers load, save, freeze, share and download weights, and 'the weights' often means the trained model file itself. An open-weight model is one whose weights are published, even if its training data and code are not.

Example sentences

  1. Download the weights from the shared drive and load them into the evaluation script.

  2. They published the weights but not the training data.

Common collocations

  • model weights
  • load the weights
  • open weights
  • freeze the weights
  • pretrained weights
  • parameterA number inside a model, such as a weight or a bias, that is learned from data during training. Model size is often given as the number of parameters.
  • neural networkA model made of many connected units arranged in layers, loosely inspired by the brain. Each connection has a weight that is adjusted during training.
  • checkpointA saved copy of a model's weights, and often its optimizer state, at a certain point in training, so that training can be resumed or that version can be used later.
  • quantizationStoring a model's weights, and sometimes its activations, with fewer bits, for example 8-bit or 4-bit numbers instead of 16-bit, to make it smaller and faster.

This word in other fields

The same English word can have a different meaning in another field:

More terms: Neural Networks and Deep Learning

Practise with graded reading

Reading at the right level is the fastest way to make new words stick. Pick free English books by level: