Back to course
Next page
Interactive Quiz
Test your knowledge!
1
What is the main purpose of cross-validation in deep learning?
A
Increase the model's training speed
B
Precisely evaluate a model over the entire training dataset
C
Reduce the dataset size for training
D
Generate new training data
2
In the k-fold cross-validation method, which parameter directly influences the number of trained models?
A
The number of classes in the dataset
B
The size of each validation subset
C
The value of k, i.e., the number of subsets
D
The model's learning rate
3
What is the main difference between stratified k-fold cross-validation and classic k-fold cross-validation?
A
Stratified k-fold uses a variable number of folds
B
Stratified k-fold maintains the same class distribution in each subset
C
Stratified k-fold does not split the dataset into subsets
D
Stratified k-fold does not require multiple training iterations
4
What is a major drawback of the leave-one-out cross-validation (LOOCV) method?
A
It cannot detect overfitting
B
It requires training the model multiple times, equal to the dataset size
C
It cannot be used for fine-tuning with small datasets
D
It does not account for class distribution
5
Which of the following is a correct advantage of cross-validation?
A
It speeds up the model training process
B
It enables more reliable model evaluation by reducing the effect of randomness in data splitting
C
It simplifies hyperparameter selection by avoiding any regularization
D
It completely eliminates the risk of overfitting
Score: 0/5
Score: 0/5