1
Which of the following is a subset of machine learning?
Correct Answer
Deep Learning
☑ MCQ PRACTICE
Neural Networks and Deep Learning Unit 3
Practice objective questions for quick revision and examination preparation. Try answering each question before revealing the answer.
Neural Networks and Deep Learning - Unit-3
2
Which of the following functions can be used as an activation function in the output layer if we wish to predict the probabilities of n classes (p1, p2..pk) such that sum of p over all n equals to 1?
Correct Answer
Softmax
3
The number of nodes in the input layer is 20 and the hidden layer is 5. The maximum number of connections from the input layer to the hidden layer are
Correct Answer
100
4
In which of the following applications can we use deep learning to solve the problem?
Correct Answer
All of the above
5
Which of the following would have a constant input in each epoch of training a Deep Learning model?
Correct Answer
Weight between input and hidden layer
6
In a classification problem, which of the following activation function is most widely used in the hidden layer of neural networks?
Correct Answer
Rectifier function
7
Which of the following is true about bias?
Correct Answer
Both A and B
8
What is the purpose of a loss function?
Correct Answer
Both A and B
9
Which of the following is a loss function?
Correct Answer
Cross entropy
10
Which of the following loss function is used in regression?
Correct Answer
Mean squared error
11
What is gradient descent?
Correct Answer
Optimization algorithm
12
What does a gradient descent algorithm do?
Correct Answer
Both A and B
13
Which of the following activation function can not be used in the output layer of an image classification model?
Correct Answer
ReLu
14
For a binary classification problem, which of the following activation function is used?
Correct Answer
Sigmoid
15
Types of Cost Function
Correct Answer
All the above
16
If you increase the number of hidden layers in a Multi Layer Perceptron, the classification error of test data always decreases.(True/ False)
Correct Answer
False
17
_____________ is a subset of Machine Learning that uses mathematical functions to map the input to the output.
Correct Answer
Deep Learning
18
A ______________ is an important parameter that determines how well a machine learning model performs for a given dataset
Correct Answer
cost function
19
__________ Functions are most often used as the output of a classifier, to represent the probability distribution over n different classes
Correct Answer
Softmax
20
Rectified linear units are an excellent default choice of _________ layer.
Correct Answer
hidden
21
Sigmoid and tanh activation functions cannot be with many layers due to the ____________ problem.
Correct Answer
vanishing gradient
22
__________ function overcomes the vanishing gradient problem, allowing models to learn faster and perform better
Correct Answer
ReLU