AI glossary
What is regularisation?
Short answer
Techniques (L2 penalty, dropout, etc.) that discourage overly complex models to reduce overfitting.
For example
Dropout randomly switches off some neurons during training, so the network can't lean too heavily on any single one and generalises better.
Learn it in a free lesson
Related terms
Questions
What is regularisation in simple terms?
Techniques (L2 penalty, dropout, etc.) that discourage overly complex models to reduce overfitting.
What is an example of regularisation?
Dropout randomly switches off some neurons during training, so the network can't lean too heavily on any single one and generalises better.
Where can I learn about regularisation for free?
AI in Bed explains it in the free lesson "Overfitting & the Goldilocks model" (Intermediate level, 5 minutes), with no sign-up.