Sigmoid Function
Squeezes any number into a range between 0 and 1.
Squeezes any number into a range between 0 and 1.
When production data diverges significantly from the training dataset
When the production data is significantly different from the training distribution.
The average absolute difference between predictions and labels — less sensitive to outliers than RMSE.
A regression metric that penalises large errors.
a subspace where the dimension is one less than the ambient space
a technique for reducing the dimensionality of data