21CS743
21CS743
Note: 01. Answer any FIVE full questions, choosing at least ONE question from each MODULE.
*Bloom’s
Module -1 Taxonomy Marks
Level COs
Q.01 a Explain the historical trends in deep learning. L2 1 10
b Define machine learning. Explain different types of ML algorithms. L3 1 10
OR
Q.02 a Explain in detail about the supervised learning approach by taking suitable ex. L2 1 10
b Write a note on support vector machine and PCA. L2 1 10
Module-2
Q. 03 a Explain the working of deep forward networks. L2 2 10
b What is regularization? How does regularization help in reducing overfitting. L3 2 10
OR
Q.04 a Explain briefly about gradient descent algorithm. L2 2 10
b Discuss the working of Backpropogation. L1 2 10
Module-3
Q. 05 a Explain Empirical risk minimization. L1 3 10
b Explain the challenges occur in neural network optimization in detail. L2 3 10
OR
Q. 06 a Explain AdaGrad and write an algorithm of AdaGrad. L2 3 10
b Explain Adam algorithm in detail. L1 3 10
Module-4
Q. 07 a Explain the components of CNN layer. L2 4 10
b Explain Pooling with network representation. L2 4 10
OR
Q. 08 a Explain the variants of the CNN model. L2 4 10
b Explain structured output with neural network. L2 4 10
Module-5
Q. 09 a Explain how the recurrunt neural network (RNN) processes data sequences. L3 5 10
b Discuss about Bidirectional RNNs. L2 5 10
OR
Q. 10 a Explain LSTM working principle along with equations. L2 5 10
b Write a note on Speech Recognition and NLP. L2 5 10
*Bloom’s Taxonomy Level: Indicate as L1, L2, L3, L4, etc. It is also desirable to indicate the COs and POs to be
attained by every bit of questions.
Page 01 of 01