Scribd
Upload
2K views2 pages

AD3501 - Deep Learning University Question

university question paper

Uploaded by

athirayanpericse
Copyright
© © All Rights Reserved
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
2K views2 pages

AD3501 - Deep Learning University Question

university question paper

Uploaded by

athirayanpericse
Copyright
© © All Rights Reserved
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
Reg. No. LJ Question Paper Code : 20015 B.EJB.Tech. DEGREE EXAMINATIONS, NOVEMBER/DECEMBER 2023. Fifth Semester Artificial Intelligence and Data Science AD 3501 ~ DEEP LEARNING (Regulations 2021) ‘Time : Three hours Maximum : 100 marks re aC 10. aL Answer ALL questions. PART A — (10 x 2= 20 marks) Differentiate supervised and unsupervised learning. What is stochastic gradient descent? What are sparse interactions in a convolutional neural network? Present an outline of pooling layer in convolutional neural network. Define a recurrent neural network, What is LSTM? How it differs from RNN? What is a baseline model in deep learning? Define random search. What is a regularized autoencoder? Define a stochastic encoder. PART B — (6 x 13 = 65 marks) (a) (Discuss the Bias - Variance trade off. o Gi) Discuss overfitting and underfitting with an example. © Or (b) Explain the operations of deep feed forward network with a diagram. (13) 12, 13. 14, 1, 16. (a) (o) @ (b) @ (a) (b) (a) What is a convolutional neural network? Outline transposed and dilated convolutions with an example. (13) Or How to introduce non-linearity in a convolutional neural network? Explain with an example. (13) What is a bi-directional recurrent neural network? Explain the architecture of a bi-directional recurrent neural network with a diagram. a3) Or What is long short term memory? Compare and contrast LSTM and gated recurred units. (13) Discuss the various performance metrics to evaluate a deep learning model with an example. (a3) Or Why are hyperparameters? Discuss the stops to perform hyperparameter tuning. (13) Justify your answer, that how autoencoders are suitable compared to Principal Compact Analysis (PCA) for dimensionality reduction. (13) Or What is a generative adversarial network? Explain the architecture of a generative adversarial network with a diagram. a3) PART C — (1x 15 = 15 marks) Discuss the various loss functions in neural networks. (5) Or Discuss the steps involved in grid search with an example, (15) 20015

You might also like