Deep learning

Q1. Which of the following are universal approximators?

Kernel SVM
All of the above
Neural Networks
Boosted Decision Trees

Q2. What are the layers in between called?

Middle layers
Hidden layers
None of these
In-between layers

Q3. ____________ is a multi-layered neural network that can store information in context nodes

All of these
RNS
RNN
RNA

Q4. Uses of RNN

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

Q5. 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 input and hidden layer
Weight between hidden and output layer
Activation function of output layer

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?

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

Q7. 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] , [ 1 X 5]
[8 X 5] , [5 X 1]
[5 x 1] , [8 X 5]
[1 X 5] , [5 X 8]

Q8. Number of layers of deep learning algorithm

5
3
2
4

Q9. Which of the following neural network training challenges can be solved using batch normalization?

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

Q10. Which of following activation functions can’t be used as output layer to classify an image ?

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

Q11. ________ is the study of computer algorithms that learn through data

None of these
Both
Computer
Machine learning

Q12. CNN

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

Q13. In which of the following applications can we use deep learning to solve the problem?

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

Q14. CNNs are suited for

None of these
Both
perceptual tasks
recurrent neural network

Q15. Deep learning teaches computer to

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

Q16. 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
ReLu
Sigmoid
Tanh

Q17. Which of the following statements is true when you use 1×1 convolutions in a CNN?

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

Q18. Deep learning is

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

Q19. Which layer is the Input layer?

middle layer
second layer
first layer
last layer

Q20. 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
less than 50
it's an arbitrary value
more than 50

Your Score

- of - questions are answered correctly

Certificate in Deep Learning

Call Us

For Support

Office Hours

We are on

Company

Customer Service

Help