You are on page 1of 6

Name

Date

Review on Machine Learning Score

1. What is the p ima y objective of a Generative Adversa ial Network?


A Image Classification

B Image genaration

C Text summa ization

D Text translation

2. What are the two main components of a GAN?


A Generator and encoder

B Disc iminator and encoder

C Generator and disc iminator

D Encoder and disc iminator

3. Which component of a GAN is responsible for generating synthetic samples?


A Generator

B Disc iminator

C Encoder

D Noise input

4. What is the training process in a GAN called?


A Supe vised lea ning

B Reinforcement lea ning

C Unsupe vised lea ning

D Adversa ial lea ning

5. How does the generator component in a GAN lea n to generate realistic samples?
A By minimizing the loss function of the disc iminator

B By maximizing the loss function of the disc iminator

C By minimizing the loss function of the generator

D By maximizing the loss function of the generator


6. How does the disc iminator component in a GAN lea n to distinguish between real and
generated samples?
A By minimizing the loss function of the generator

B By maximizing the loss function of the generator

C By minimizing the loss function of the disc iminator

D By maximizing the loss function of the disc iminator

7. What is mode collapse in GANs?


A When the generator produces limited va iations of samples

B When the disc iminator fails to distinguish between real and generated samples

C When the GAN training process becomes unstable

D When the generator and disc iminator achieve pe fect equilib ium

8. What is the purpose of noise input in the generator component of a GAN?


A To randomize the generation process and introduce va iations

B To control the lea ning rate du ing training

C To adjust the weights and biases of the generator

D None of the above

9. What is the role of the disc iminator in a GAN du ing the training process?
A To provide feedback to the generator and help it improve

B To generate synthetic samples

C To adjust the lea ning rate du ing training

D None of the above

10. Which type of GAN is designed to generate samples conditioned on specific input
info mation?
A Vanilla GAN

B Wasserstein GAN

C Deep Convolution GAN

D Conditional GAN
11. What is the purpose of the conditional input in a conditional GAN?
A To control the characte istics of generated samples

B To adjust the lea ning rate du ing training

C To adjust the weights and biases of the generator

D None of the above

12. What is full fo m of ANNs?


A A tificial Neural Node

B AI Neural Networks

C A tificial Neural Networks

D A tificial Neural numbers

13. What is perceptron?


A a single layer feed-fo ward neural network with pre-processing

B an auto-associative neural network

C a double layer auto-associative neural network

D a neural network that contains feedback

14. A 4-input neuron has weights 1, 2, 3 and 4. The


transfer function is linear with the constant of propo tionality being
equal to 2. The inputs are 4, 3, 2 and 1 respectively. What will be the
output?
A 30

B 40

C 50

D 60

15. Which of the following is not the promise of a tificial neural network?
A It can explain result

B It can su vive the failure of some nodes

C It has inherent parallelism

D It can handle noise


16. The output at each node is called_____?
A node value

B weight

C neurons

D axons

17. The complexity of ANN is dependent upon?


A Number of Neurons

B Number of Nodes

C Number of Layers

D Activation function

18. How many outcomes are produced from a tificial neurons?


A 1

B 2

C 5

D Multiple

19. Which layer in ANN can receive data from exte nal sources?
A Input layer

B Hidden layer

C Output layer

D All of these

20. 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 mat ices between hidden output
layer and input hidden layer?
A 1x5 , 5x8

B 5x1 , 8x5

C 8x5 , 5x1

D 8x5 , 1x5
21. Which of the following is/are Limitations of Deep Lea ning?
A Need Data Labeling

B Need huge training datasets

C Both A and B

D None of these

22. Suppose your input is a 300 by 300 color RGB image, and you use a convolutional layer
with 100 filters that are each 5x5. How many parameters does this hidden layer have (without
bias)
A 2501

B 2600

C 7500

D 7600

23. You have an input volume that is 63x63x16, and convolve it with 32 filters that are each 7x7,
using st ide of 2 and no padding. What is the output volume?
A 16x16x32

B 29x29x16

C 29x29x32

D 16x16x16

24. You have an input volume that is 15x15x18, and pad it using "padding=2". What is the
dimension of the resulting volume?
A 19x19x12

B 17x17x10

C 19x19x8

D 17x17x8

25. Which activation function is commonly used in the convolutional layers of a CNN?
A ReLU

B Sigmoid

C tanh

D Softmax
26. What is the purpose of the st ide parameter in a convolutional layer?
A To dete mine the size of the receptive field

B To control the step size of the convolution operation

C To adjust the lea ning rate du ing training

D None of the above

27. Which layer type is used to reduce the spatial dimensions in a CNN?
A Convolutional layer

B Pooling layer

C Fully connected layer

D Activation layer

28. What is the purpose of the padding parameter in a convolutional layer?


A To adjust the lea ning rate du ing training

B To prevent the reduction of spatial dimensions

C To regula ize the network and prevent ove fitting

D None of the above

29. Which layer type is responsible for making final predictions in a CNN?
A Convolutional layer

B Pooling layer

C Fully connected layer

D Activation layer

30. Which layer type is responsible for applying non-linear transfo mations to the feature maps in
a CNN?
A Convolutional layer

B Pooling layer

C Fully connected layer

D Activation layer

You might also like