AKTU Deep Learning (KCS078) Question Paper 2022-23

Note: Attempt all Sections. If you require any missing data, then choose suitably.

Section A

Q1. Attempt all questions in brief · 2 × 10 = 20 marks

1. What are the applications of Machine Learning?
2. Describe the Boltzmann Machine.
3. Is it possible to build deep learning models based solely on linear regression? Explain.
4. Define the different layers of a convolutional neural network.
5. Explain the linear models
6. Why is it important to introduce non-linearities in a neural network?
7. What are the limitations of using a perceptron?
8. Why do we use convolutions for images instead of using fully connected layers?`
9. Why are GPUs important for implementing deep learning models?
10. Which is the best algorithm for face detection ?

Section B

Q2. Attempt any three of the following · 10 × 3 = 30 marks

1. Difference between Deep and Shallow Network.
2. Draw and explain the architecture of Convolutional Networks.
3. Why CNN is preferred over ANN for Image Classification tasks even though it is possible to solve image classification using ANN?
4. Explain LSTM (Long Short Term Memory ). Give some famous applications of LSTM.
5. Explain Image Captioning in Deep Learning.

Section C

Q3

Attempt any one part of the following · 10 × 1 = 10 marks

1. Explain the difference between Gradient Descent and Stochastic Gradient Descent.
2. ExplainGAN and its models. Name and describe different types of GANs.

Q4

Attempt any one part of the following · 10 × 1 = 10 marks

1. Examine the Semi –Supervised learning.
2. Demonstrate deep learning. Explain its uses, application and history.

Q5

Attempt any one part of the following · 10 × 1 = 10 marks

1. Explain Back propagation with its algorithm.
2. Write short notes :- i) Deep Reinforcement ii) Autoencoder Architecture iii) VGG iv) SOA

Q6

Attempt any one part of the following · 10 × 1 = 10 marks

1. Compare PCA (Principle Component Analysis ) and RNN.
2. Discuss how batch gradient descent and stochastic gradient descent are different.

Q7

Attempt any one part of the following · 10 × 1 = 10 marks

1. Demonstrate how the privacy will be affected when facial recognition gets used by private companies?
2. How AI and Neuroscience drive each other forwards? Explain.

Short on time? See the most repeated AKTU Deep Learning questions across all years.

Other years

More AKTU Deep Learning papers on LearnAIFast.

This paper is reproduced for study purposes only. Copyright belongs to AKTU. Source: the question paper bank of ABES Institute of Technology, an AKTU-affiliated college. If you own the copyright and want it removed, email learnwithskillnest@gmail.com and we will take it down.