AI engineering glossary · Deep learning core
What is validation loss?
Validation loss: The loss measured on held-out data that the network does not train on. Watching it alongside training loss reveals overfitting: training loss keeps falling while validation loss stops improving or rises.
Validation loss: an example
Training loss of 0.1 with validation loss climbing from 0.4 to 0.6 across epochs signals memorisation.
Related terms
More Deep learning core terms
- Vanishing gradient
- Weight decay
- Weight initialisation
- Weight normalisation
- Weight sharing
- Weight tying
- Xavier initialisation
- Activation function
Where you learn it
Validation loss is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.