A lock-tender narrative classifier memorizes clerk names that appear in the training notes and then fails on new crews. The architecture is a neural net, not a linear model. Which regularization technique fits?
Select an answer to reveal the explanation.
Short Explanation
Think of a narrative classifier that memorizes clerk names and fails on new crews. The architecture is a neural net. Dropout. More epochs just memorize the names harder.
Full Explanation
Dropout is a regularization technique that reduces overfitting in a neural network by randomly dropping units during training. More epochs deepen the memorization. Comprehend is not dropout, and Linear Learner is a different architecture.