Skip to content
AD-304 · Artificial Intelligence/Unsolved PYQ Paper

ARTIFICIAL INTELLIGENCE - MAY 2024 Question Paper

  1. Unit 1
    7 Marks
    aExplain the structure and function of a biological neuron compared to an artificial neuron.
  2. Unit 1
    7 Marks
    bHow does the McCulloch-Pitts Neuron model contribute to the development of artificial neural networks? Explain.
  3. Unit 1
    7 Marks
    aDescribe the architecture and operation of Rosenblatt's Perceptron model in the context of neural networks.
  4. Unit 1
    7 Marks
    bHow does the back propagation algorithm enable the neural network to adjust its weights and biases during training? Explain with example.
  5. Unit 1
    7 Marks
    aExplain the process of gradient descent and its variations like momentum in the context of optimizing neural network parameters.
  6. Unit 1
    7 Marks
    bDiscuss in detail the concept of layers in an artificial neural network and the specific roles of input, hidden, and output layers?
  7. Unit 1
    7 Marks
    aDescribe the purpose and construction of a confusion matrix in the context of evaluating classification performance in CNNs.
  8. Unit 1
    7 Marks
    bDescribe the various types of layers used in CNNs? How does it differ? Explain.
  9. Unit 1
    7 Marks
    aExplain the significance of padding and stride in convolutional operations within CNNs, and how do they affect the output?
  10. Unit 1
    7 Marks
    bExplain the concept of bidirectional RNNs and how they differ from traditional RNNs in terms of information processing.
  11. Unit 1
    7 Marks
    aHow does Back Propagation Through Time (BPTT) enable RNNs to learn from sequential data, and what challenges does it face? Explain in detail.
  12. Unit 1
    7 Marks
    bDiscuss the architecture and functioning of Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) units within RNNs, highlighting their differences and advantages.
  13. Unit 1
    7 Marks
    aCompare and contrast the architectural differences between VGG-16 and GoogLeNet, highlighting their strengths and weaknesses in handling complex image recognition tasks.
  14. Unit 1
    7 Marks
    bExplain the concept of residual learning in ResNet architectures and how it addresses the challenge of training neural networks.
  15. Unit 1
    14 Marks
    Write a short note on any two : i) Sigmoid ii) Precision iii) F1-score iv) MNIST data set
Go to where you left off?

Quick Add to Notes

Save questions, your own notes and screenshots into notes filed by unit. It takes a free account.

Create free account

Have an account? Log in