Deep learning

Q1. Which of the following would have a constant input in each epoch of training a Deep Learning model?

Biases of all hidden layer neurons
Weight between hidden and output layer
Weight between input and hidden layer
Activation function of output layer

Q2. In which of the following applications can we use deep learning to solve the problem?

Protein structure prediction
Detection of exotic particles
Prediction of chemical reactions
All of the above

Q3. 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?

Softmax
Sigmoid
ReLu
Tanh

Q4. Deep learning teaches computer to

learn by example
Both
None of these
to perform classification tasks directly from images, text, or sound

Q5. CNNs are suited for

Both
perceptual tasks
recurrent neural network
None of these

Q6. The number of nodes in the input layer is 10 and the hidden layer is 5. The maximum number of connections from the input layer to the hidden layer are

it's an arbitrary value
50
less than 50
more than 50

Q7. What are the layers in between called?

Hidden layers
In-between layers
Middle layers
None of these

Q8. CNN

convolutional neural network
None of these
converted neural network
covolutional net network

Q9. Which of the following are universal approximators?

Neural Networks
All of the above
Kernel SVM
Boosted Decision Trees

Q10. Deep learning is

subset of machine learning
computer software that mimics the network of neurons in a brain
None of these
Both

Q11. Which of the following statements is true when you use 1×1 convolutions in a CNN?

All of the above
It can help in dimensionality reduction
It suffers less overfitting due to small kernel size
It can be used for feature pooling

Q12. ________ is the study of computer algorithms that learn through data

Both
Machine learning
None of these
Computer

Q13. Uses of RNN

BusinessesHelp securities traders to generate analytic reports
All of these
Provide a caption for images
Detect fraudulent credit-card transaction

Q14. Which of following activation functions can’t be used as output layer to classify an image ?

Sigmoid
If(x>5,1,0)
Tanh
ReLU

Q15. Which layer is the Input layer?

second layer
middle layer
first layer
last layer

Q16. ____________ is a multi-layered neural network that can store information in context nodes

RNA
RNN
All of these
RNS

Q17. Which of the following neural network training challenges can be solved using batch normalization?

Overfitting
Training is too slow
Restrict activations to become too high or low
Both B and C

Q18. The input image has been converted into a matrix of size 28 X 28 and a kernel/filter of size 7 X 7 with a stride of 1. What will be the size of the convoluted matrix?

21 X 21
22 X 22
28 X 28
7 X 7

Q19. In a simple MLP model with 8 neurons in the input layer, 5 neurons in the hidden layer and 1 neuron in the output layer. What is the size of the weight matrices between hidden output layer and input hidden layer?

[8 X 5] , [5 X 1]
[1 X 5] , [5 X 8]
[5 x 1] , [8 X 5]
[8 X 5] , [ 1 X 5]

Q20. Number of layers of deep learning algorithm

5
3
4
2

Your Score

- of - questions are answered correctly

Certificate in Deep Learning

For Support

Office Hours

We are on

Company

Customer Service

Help

Your Score

- of - questions are answered correctly

Login to view answer sheet

FORGOT PASSWORD

SIGN UP

Email Verification