Scribd
Upload
279 views

Deep Learning Question Bank(2024-25)

Uploaded by

bhavani
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
279 views

Deep Learning Question Bank(2024-25)

Uploaded by

bhavani
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Deep Learning(22MCA3PE51)

QUESTION BANK (2024-25)


Q.N Question Marks
o
Module-I
1 Define Machine Learning. Explain different types of learning 10
algorithms in ML.
2 Explain the structure and learning process of a single-layer perceptron, 10
and discuss its limitations as a pattern classifier.
3 Explain the structure and learning process of a multilayer perceptron, 10
and
explain how it can be used to solve complex pattern recognition
problems.
4 Explain the architecture of Artificial Neural Network. How do Artificial 10
Neural Networks Learn.
5 Write and explain multilayer perceptron algorithm. 10
6 Explain Logistic Regression. 8
7 Briefly explain Support Vector Machine. 8
8 What is loss function. Explain different types of loss functions. 10
9 Discuss Back Propagation and Stochastic Gradient Descent. 10

Module-II
1 Briefly explain Back Propagation Network algorithm. 10
2 What is regularization. Explain different types of regularization. 10
3 Briefly explain L1 regularization. 8
4 Briefly explain L2 regularization. 8
5 Differentiate between L1 and L2 Regularization. 8
6 What is Batch Normalization? Discuss the procedure to do batch 10
normalization.
7 Explain Shallow Networks? 10
8 Differentiate between shallow Net and Deep Learning Net. 6

Module-III
1 What is dimensionality reduction? Explain the steps involved in 10
computing the principal components in PCA (Principal Component
Analysis).
2 Discuss the importance of Principal Component Analysis. 10
3 List and explain any 3 advantages and disadvantages of Principal 6
Component Analysis.
4 Discuss LDA(Linear Discriminant Analysis). Explain steps involved in 10
LDA.
5 Discuss any three advantages and disadvantages of LDA. 6
6 Explain Manifold Learning. 10
7 Explain autoencoders with a neat diagram. 10
8 With a neat diagram, explain the architecture of AlexNet. 8
9 With a neat diagram explain the architecture of VGG-16. 8
10 With a neat diagram explain the architecture of ResNet. 8
11 Explain the architecture of CNN in detail. 8
12 What is hyper parameter optimization? Elucidate various hyper 8
parameter optimization methods.

Module-IV
1 What is optimization? Explain Convex and Non-Convex optimization 10
techniques.
2 With a neat diagram explain Spatial Transformation Networks(STN). 10
3 Discuss RNN (Recurrent Neural Network) with a neat diagram. 10
4 Discuss Long Short Term Memory (LSTM) Networks also explain 10
steps involved in networks.
5 List out various applications of LSTM. 2

Module-V
1 Discuss in detail about ImageNet.(3) 10
2 Describe the structure and Workflow of WaveNet model with a neat 10
diagrams.
3 Draw a diagram to show NLP Phases and explain it briefly. 10
4 What is Word2Vec model? Explain the working process of Word2Vec 10
Model and its types.
5 Provide a detailed case study on joint detection using deep learning. 10
Discuss the steps involved.
6 Provide a detailed case study on Face Recognition using deep learning. 10
Discuss the steps involved.

You might also like