Scribd
Upload
13 views4 pages

Viva Questions-Dllab

Uploaded by

Vivek Namboothiry
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
13 views4 pages

Viva Questions-Dllab

Uploaded by

Vivek Namboothiry
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Viva Questions

1. What is Deep Learning?


2. What is a Neural Network?
3. What is Multilayer Perceptron and How it is different from a single-layer perceptron?
4. What Is the Role of Activation Functions in a Neural Network?
5. What Is the Cost Function?
6. What Is Gradient Descent?
7. What is forward and backward propagation?
8. What Is the Difference Between a Feedforward Neural Network and Recurrent Neural
Network?
9. What Are the Softmax and ReLU Functions?
10. What Are Hyperparameters?
11. What Will Happen If the Learning Rate Is Set Too Low or Too High?
12. What Is Dropout and Batch Normalization?
13. What Is the Difference Between Batch Gradient Descent and Stochastic Gradient
Descent?
14. What is Overfitting and Underfitting, and How to Combat Them?
15. How Are Weights Initialized in a Network?
16. What Are the Different Layers on CNN?
17. What is Pooling on CNN, and How Does It Work?
18. What Are Vanishing and Exploding Gradients?
19. What Is the Difference Between Epoch, Batch, and Iteration in Deep Learning?
20. What Is Bagging and Boosting?
21. What is Data Augmentation in Deep Learning?
22. Explain the Adam optimization algorithm.
23. Why is a convolutional neural network preferred over a dense neural network for an
image classification task?
24. Why is a deep neural network better than a shallow neural network?
25. What is the need to add randomness in the weight initialization process?
26. What are the main differences between AI, Machine Learning, and Deep Learning?
27. Differentiate supervised and unsupervised deep learning procedures.
28. What are the applications of deep learning?

29. What is Backpropagation?

30. What are the deep learning frameworks or tools?

31. What are the disadvantages of deep learning?

32. What is the meaning of term weight initialization in neural networks?

33. Why is zero initialization not a good weight initialization process?

34. How many layers in the neural network?

35. What is the use of the Activation function?

36. How many types of activation function are available

37. What is a binary step function?

38. What is the sigmoid function?

39. What is Tanh function?


40. What is ReLU function?

41. What is the use of leaky ReLU function?

42. What is the softmax function?

43. What is the most used activation function?

44. Can Relu function be used in output layer?

45. In which layer softmax activation function used?

46. What do you mean by Dropout?

47. What do you understand by Perceptron? Also, explain its type.

48. How does Deep Learning differ from Machine Learning?

49. What are the applications of Deep Learning?

50. What are the challenges in Deep Learning?

51. How Biological neurons are similar to the Artificial neural network.

52. How deep learning is used in supervised, unsupervised as well as reinforcement


machine learning?

53. What is a Perceptron?

54. What are Feedforward Neural Networks?

55. What is GPU?

56. What are the different layers in ANN? What is the notation for representing a node of
a particular layer?

57. How do neural networks learn from the data?

58. How the number of hidden layers and number of neurons per hidden layer are
selected?

59. Define the learning rate in Deep Learning.

60. What is the Cross-Entropy loss function?

61. How do you optimize a Deep Learning model?


62. What do you mean by momentum optimizations?

63. What is gradient descent?

64. What do you mean by vanishing or exploding gradient descent problem?

65. How weights are initialized in neural networks?

66. Define Batch, Stochastic, and Mini gradient descent.

67. What do you mean by Batch Normalization?

68. What is a dropout in Deep Learning?

69. What are the different types of Neural Networks?

70. What do you mean by convolution?

71. What is a kernel?

72. Define stride.

73. What is the pooling layer?

74. Define the same and valid padding.

75. What do you mean by deconvolution?

76. What is the difference between object detection and image segmentation?

77. What is LSTM, and How it works?

78. What is GRU, and How it works?

79. What is BERT, and How it works?

80. What is an autoencoder?

81. What is a Generative Adversarial Network (GAN)?

82. What is Transfer Learning?


83. Explain a Computational Graph

84. What Is Bagging and Boosting?

85. What are some of the uses of Autoencoders in Deep Learning?

86. Why is a convolutional neural network preferred over a dense neural network for an
image classification task?

87. Which strategy does not prevent a model from over-fitting to the training data?

88. What are the applications of deep learning?

89. What are the deep learning frameworks or tools?

90. What do you understand by Tensors?

91. What do you understand by Boltzmann Machine?

92. What are the issues faced while training in Recurrent Networks?

93. What are the different layers of Autoencoders? Explain briefly.

94. What do you understand by Deep Autoencoders?

95. What is Restricted Boltzmann Machine?

96. What is Deep Belief Network?

97. What is Hopfield network?

98. When should you choose deep learning over machine learning solutions?

99. How would you choose the right deep learning approach for your problem and data?

100. What are the different types of deep neural networks?

You might also like