1
Batch normalization helps to prevent
Correct Answer
Both A and B
☑ MCQ PRACTICE
Neural Networks and Deep Learning Unit 4
Practice objective questions for quick revision and examination preparation. Try answering each question before revealing the answer.
Neural Networks and Deep Learning - Unit-4
2
Which of the following is true about dropout?
Correct Answer
Applied in the hidden layer nodes
3
Which of the following steps can be taken to prevent overfitting in a neural network?
Correct Answer
All of the above
4
Which of the following methods DOES NOT prevent a model from overfitting to the training set?
Correct Answer
Pooling
5
Methods comes under Data augmentation
Correct Answer
All the above
6
Which of these techniques are useful for reducing variance (reducing overfitting)?
Correct Answer
Dropout
7
Why do we normalize the inputs x?
Correct Answer
It makes the cost function faster to optimize
8
Which of the following is true about bagging?
Correct Answer
All the above
9
Because of low bias and high variance , we get _____ model
Correct Answer
over fitting
10
Higher the dropout rate, lower is the regularization(True/ False)
Correct Answer
True
11
Noise applied to inputs is a _______________
Correct Answer
data augmentation
12
____________ Learning algorithm is trained upon a combination of labeled and unlabelled data
Correct Answer
Semi-Supervised
13
L2 regularization is also known as ___________
Correct Answer
ridge regression
14
The __________ regularization which pushes the value of weight to zero.
Correct Answer
L1
15
__________ is a way to improve generalization by the examples arising out of several tasks
Correct Answer
Multi-task learning
16
The algorithm terminates when no parameters have improved over the best recorded validation error for some pre-specified number of iterations, This strategy is known as ____________
Correct Answer
early stopping
17
_________ may be used either alone or in conjunction with other regularization strategies.
Correct Answer
Early stopping
18
________ is a technique for reducing generalization error by combining several models
Correct Answer
Bagging