Pages
Problems in Training
Overfitting & Underfitting
What is Overfitting
Overfitting is when the neuralnet changes to adapt so much to a specific set of data.
Overfitting happens when
Prevent Overfitting
Use Data Split
Split training data into training set and test set.
Use Regularisation
To limit weight range into a small range, the rest of the range for weight values should be for those training sample unknown yet.
Underfitting
Underfitting is the case that the model has not been trained enough. The model in such case doesn’t give good results for known data nor good results for unknown data.
Want to print your doc?
This is not the way.
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.