Okuzeka
Software Engineering vocabulary · Machine Learning and Data Processing

Converge

Meaning in software engineering, with examples

/kənˈvɜːrdʒ/verbCommon term

In software engineering, converge means: To reach a stable state during training, where the loss stops going down in a meaningful way and more training brings little benefit.

In Turkish: yakınsamak, oturmak

How it is used

Said of models, training runs and losses: 'the model converged after 20 epochs', 'the loss isn't converging'. The noun is convergence. When training never converges, people check the learning rate, the data and the code.

Example sentences

  1. The model converged after about 12 epochs, so we stopped there.

  2. With the new learning rate, training converges twice as fast.

Common collocations

  • converge quickly
  • fail to converge
  • training converges
  • convergence speed
  • loss functionA formula that measures how far a model's predictions are from the correct answers. Training tries to make this value, called the loss, as small as possible.
  • learning rateA hyperparameter that controls how big a step the model takes each time it updates its parameters. Too high makes training unstable; too low makes it very slow.
  • epochOne complete pass of the training process through the whole training dataset. Models are usually trained for several epochs.
  • gradient descentThe basic optimization method behind training: it repeatedly changes each parameter a little in the direction that reduces the loss the most.

This word in other fields

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

More terms: Machine Learning and Data Processing

Practise with graded reading

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