Code No: R204105E R20 Set No.
1
IV B.Tech I Semester Regular Examinations, January – 2024
DEEP LEARNING TECHNIQUES
(PE-IV: EEE, CSE, IT) (OE-IV: CE, ME, ECE, AME, MM, AGE, CSE-CS, CSE-IOTCSIBCT,
CSE-IOT, FE, PHARM & CS)
Time: 3 hours Max. Marks: 70
Answer any FIVE Questions
ONE Question from Each unit
All Questions Carry Equal Marks
*****
UNIT - I
1 a) Is AI a science or is it engineering? Or neither or both? Explain. [7]
b) Write down present and future scope of AI. [7]
(OR)
2 a) What are kernel methods in Deep learning? Explain. [7]
b) Write down brief history and evolution of AI. [7]
UNIT - II
3 a) Discuss about types of Optimizers. [7]
b) Explain the difference between AI, ML and DL. [7]
(OR)
4 a) How to improve Deep learning using weight initialization. [7]
b) Explain the Google duplex project. [7]
UNIT - III
5 a) Explain different types of neural networks. [7]
b) Explain the terms loss function and optimizers with respect to DL. [7]
(OR)
6 a) Explain the steps in setting up the deep learning workstation. [7]
b) What is the best GPU for deep learning? Explain in detail. [7]
UNIT - IV
7 a) Explain about filters in CNN’s. [7]
b) Explain about BPTT algorithm. [7]
(OR)
8 a) Discuss about neural networks and representation learning. [7]
b) Explain the differences between ANN and CNN. [7]
UNIT - V
9 a) What are the regular algorithms used in NLP. [7]
b) Discuss about training the dataset in GAN’s [7]
(OR)
10 a) What are some advantages of using machine vision over regular
human inspection? [7]
b) Explain the types of GAN’s. [7]
1 of 1
|''|''|||''|'''|||'|
Code No: R204105E R20 Set No. 2
IV B.Tech I Semester Regular Examinations, January – 2024
DEEP LEARNING TECHNIQUES
(PE-IV: EEE, CSE, IT) (OE-IV: CE, ME, ECE, AME, MM, AGE, CSE-CS, CSE-IOTCSIBCT,
CSE-IOT, FE, PHARM & CS)
Time: 3 hours Max. Marks: 70
Answer any FIVE Questions
ONE Question from Each unit
All Questions Carry Equal Marks
*****
UNIT - I
1 a) Define in your own words the terms: state, state space, search tree, Search node. [7]
b) Explain the terms Over fitting and Under fitting in ML. [7]
(OR)
2 a) How random forests are related to Decision trees. [7]
b) What are the assumptions of Gradient boosting Algorithm? [7]
UNIT - II
3 a) What is optimization? What are the measures used to minimise cost. [7]
b) Explain the deep learning network architecture. [7]
(OR)
4 a) Compare traditional machine learning approaches with current deep
learning approaches. [7]
b) Explain about biological vision and machine vision. [7]
UNIT - III
5 a) Plot the graph between training (i.e no. of epochs) and validation loss. Explain. [7]
b) Explain the anatomy of a neural network. [7]
(OR)
6 a) Elaborate on Reuters dataset in detail. [7]
b) Inspect the implementation of binary classification. [7]
UNIT - IV
7 a) Explain about the features of PyTorch library. [7]
b) Explain the term Gated recurrent units in RNN’s. [7]
(OR)
8 a) Explain in detail about LSTM in RNN. [7]
b) Explain why to use Recurrence neural networks other than CNN’s. [7]
UNIT - V
9 a) Can you explain how an image sensor is in context with machine vision? [7]
b) Explain about Natural Language Processing. [7]
(OR)
10 a) How do GAN’s work? [7]
b) Explain about various NLP tools. [7]
1 of 1
|''|''|||''|'''|||'|
Code No: R204105E R20 Set No. 3
IV B.Tech I Semester Regular Examinations, January – 2024
DEEP LEARNING TECHNIQUES
(PE-IV: EEE, CSE, IT) (OE-IV: CE, ME, ECE, AME, MM, AGE, CSE-CS, CSE-IOTCSIBCT,
CSE-IOT, FE, PHARM & CS)
Time: 3 hours Max. Marks: 70
Answer any FIVE Questions
ONE Question from Each unit
All Questions Carry Equal Marks
*****
UNIT - I
1 a) How can you improve the performance of the Gradient Boosting Algorithm? [7]
b) What is a Decision tree algorithm? Explain. [7]
(OR)
2 a) How is it possible to perform un-supervised learning with Random Forest? [7]
b) Explain how random forests give output for classification and regression
problems. [7]
UNIT - II
3 a) Explain about Adaptive gradient algorithm. [7]
b) Explain the terms forward and backward propagation in ML. [7]
(OR)
4 a) Illustrate on computation representation of language in Human and Machine
language. [7]
b) Enumerate the concept of L1 and L2 regularization in detail. [7]
UNIT - III
5 a) Discuss about keras workflow. [7]
b) Explain the terms loss function and optimizers with respect to DL. [7]
(OR)
6 a) Explain about the architecture of Keras. [7]
b) Explain the concept “Deep learning with Cloud”. [7]
UNIT - IV
7 a) Discuss about PyTorch Vs TensorFlow. [7]
b) Explain about multi-channel convolutional operation in neural networks. [7]
(OR)
8 a) Explain about convolutional operation in neural networks. [7]
b) What do you mean by weight sharing? Explain weight sharing in CNNs. [7]
UNIT - V
9 a) What are Boltzmann machines and Restricted Boltzmann machines? [7]
b) Explain about Machine vision libraries. [7]
(OR)
10 a) What are the differences between GAN and Auto-encoders? [7]
b) What are the steps involved in typical deep reinforcement learning algorithm. [7]
1 of 1
|''|''|||''|'''|||'|
Code No: R204105E R20 Set No. 4
IV B.Tech I Semester Regular Examinations, January – 2024
DEEP LEARNING TECHNIQUES
(PE-IV: EEE, CSE, IT) (OE-IV: CE, ME, ECE, AME, MM, AGE, CSE-CS, CSE-IOTCSIBCT,
CSE-IOT, FE, PHARM & CS)
Time: 3 hours Max. Marks: 70
Answer any FIVE Questions
ONE Question from Each unit
All Questions Carry Equal Marks
*****
UNIT - I
1 a) Discuss about Probabilistic modelling in detail. [7]
b) Describe the role of Artificial Intelligence in Natural Language Processing. [7]
(OR)
2 a) How is it possible to perform un-supervised learning with Random Forest? [7]
b) Interpret the concept of Underfitting with a suitable example. [7]
UNIT - II
3 a) How to know if our model is suffering from the Exploding/Vanishing gradient
problem. [7]
b) Elaborate on various cost functions used in training deep networks. [7]
(OR)
4 a) What is optimization? What are the measures used to minimise cost. [7]
b) Discuss about the Softmax layer of a Fast Food – classifying Network. [7]
UNIT - III
5 a) Discuss the classification of newswires and explain with the dataset. [7]
b) With a neat sketch, enumerate the concept of the deep-learning software and
hardware stack. [7]
(OR)
6 a) Explain the high-level building blocks required for developing deep-learning
models. [7]
b) Explain different types of neural networks. [7]
UNIT - IV
7 a) What are the advantages of using Convolutional neural networks over other
neural networks. [7]
b) How CNN’s and RNN’s works with PyTorch. [7]
(OR)
8 a) Implement stride and padding with a practical example. [7]
b) Enumerate the concept of sequence learning problems. [7]
UNIT - V
9 a) What is Deep-Net in Deep learning? [7]
b) How do Restricted Boltzmann Machines work. [7]
(OR)
10 a) What are the advantages of Deep belief networks [7]
b) Discuss in detail about Denoising Auto encoders with a suitable example. [7]
1 of 1
|''|''|||''|'''|||'|