We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 2
‘Total No. of Questions : 8] SEAT No. ;
PA-947 [Total No. of Pages : 2
[5927]-393
B.E. (Information Technology)
DEEP LEARNING
(2019 Pattern) (Semester - VII) (414443)
Time : 2% Hours] ‘[Max. Marks : 70
Instructions to the candidat
L) Answer Q.1 or 0.2, 0.3 or Q4, 0.5 oF 0.6, 0.7 or Q.8.
2) Neat diagrams must be drawn wherever necessary.
3) Figures to the right indicate full marks.
4 Assume suitable data, if necessary.
QI) a)
b)
Q2) a)
b)
Q3) a)
b)
Q4) a)
b)
Q5) a)
b)
Differentiate between feed-forward neural networks and recurrent neural
networks. Explain the types of Recurrent Neural Network (RNN). [9]
Explain how sequence to sequence model works 19]
OR
Describe the general layout of a Long Short-Term Memory Network
(LSTM) with suitable diagram. 19]
What is Recurrent Neural Network (RNN)? State and explain types of
RNN in brief. 1]
Autoencoders use unsupervised leaning approach, Justify the statement.
19]
Explain the concept of contractive autoencoder and its need. 13]
OR
State the applications of Autocncoders. Explain how the dimensionality
reduction feature of autoencoder is useful in information retrieval task?[9]
Explain denoising autoencoders with suitable figure, 18]
Why is the network called Greedy Layer Wise Pretraining Network? [9]
State and Justify Role of Representation Learning. 1p]
OR
PIO.Q6) a)
b)
Q7) a)
b)
8) a)
b)
Explain distributed representation with example. 19]
Justify when to use domain adaptation and when to use transfer learning.
19)
Explain graph convolution approach for social network analysis? Describe
RNN based framework for NLP. Write any four applications of NLP.[9]
What are the application areas of image classification? Explain CNN for
image Classification. [8]
OR
Explain content based, collaborative and hybrid recommender system
with pros and cons. 19]
Explain basic architecture of Automatic Speech Recognition system.
Why RNN is suitable for speech recognition? How bidirectional RNNs
are used in automatic speech recognition? [8]
CBS WW
[5927]-393 2