Check your understanding of this module before moving on.
?
0/3
Checkpoint quiz 3 questions
A quick check on this module's key ideas before you move on
Question 01
Why are deep neural networks especially prone to overfitting compared to simpler models?
A is correct. A network with millions of parameters has enough capacity to essentially memorize a finite training set if not constrained, which is why regularization techniques matter more as model capacity grows.
Question 02
What is the telltale sign of overfitting when monitoring training and validation loss curves during training?
B is correct. A growing gap, where training loss keeps falling but validation loss stalls or rises, is the classic signature that the model is starting to memorize training-specific quirks rather than general patterns.
Question 03
Why does simply adding more training data tend to reduce overfitting?
A is correct. Memorizing a small dataset is easy for a high-capacity model; memorizing a much larger and more varied one is much harder, so the model is pushed toward learning the actual underlying signal instead.