Deep learning

Q1. CNNs are suited for

recurrent neural network
None of these
Both
perceptual tasks

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

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

Q3. 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?

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

Q4. Deep learning is

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

Q5. What are the layers in between called?

None of these
In-between layers
Hidden layers
Middle layers

Q6. 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

Q7. Uses of RNN

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

Q8. Which of the following statements is true when you use 1×1 convolutions in a CNN?

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

Q9. Which of following activation functions can’t be used as output layer to classify an image ?

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

Q10. Which of the following neural network training challenges can be solved using batch normalization?

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

Q11. Which layer is the Input layer?

first layer
last layer
middle layer
second layer

Q12. 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

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

Q13. ____________ is a multi-layered neural network that can store information in context nodes

RNN
All of these
RNS
RNA

Q14. CNN

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

Q15. 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?

ReLu
Tanh
Sigmoid
Softmax

Q16. Number of layers of deep learning algorithm

2
4
3
5

Q17. ________ is the study of computer algorithms that learn through data

Computer
Both
Machine learning
None of these

Q18. Which of the following are universal approximators?

Neural Networks
Kernel SVM
All of the above
Boosted Decision Trees

Q19. Deep learning teaches computer to

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

Q20. Which of the following would have a constant input in each epoch of training a Deep Learning model?

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

Your Score

- of - questions are answered correctly

Certificate in Deep Learning

Call Us

For Support

Office Hours

We are on

Company

Customer Service

Help