SRM VALLIAMMAI ENGINEERING COLLEGE

(An Autonomous Institution)

SRM Nagar, Kattankulathur – 603 203

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

QUESTION BANK

VIII SEMESTER

1904801 DEEP LEARNING

Regulation – 2019

Academic Year 2022 – 2023(EVEN)

Prepared by

Mr. N. LEO BRIGHT TENNISSON (AP Sr. G. / CSE)

1
 SRM VALLIAMMAI ENGINEERING COLLEGE
(An Autonomous Institution)
SRM Nagar, Kattankulathur-603203
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

QUESTION BANK

SUBJECT :1904801 DEEP LEARNING

SEM/YEAR : VIII/IV
UNIT - I: INTRODUCTION TO MACHINE LEARNING BASICS
Scalars – Vectors – Matrices – Tensors – Identity and Inverse Matrices – Linear Dependence and Span
– Eigen Decomposition – Probability – Random Variables – Conditional Probability – Expectation –
Variance – Covariance –Bayes’ Rule – Supervised Learning Algorithm – Unsupervised Learning
Algorithm –Stochastic Gradient Descent.
PART – A

Q.N Question BT Competence

o Level
1 What is Deep Learning? BTL-1 Remember
2 Differentiate scalar and vector. BTL-2 Understand

3 Compare Deep Learning and rule based system. BTL-4 Analyze

4 What is Auto encoder? BTL-1 Remember
5 List out the special kind of matrices. BTL-1 Remember
6 What is representation learning? BTL-1 Remember
7 Compare Deep Learning with Machine learning. BTL-5 Evaluate
8 State the Bayes rule. BTL-1 Remember
9 List out some supervised learning algorithms. BTL-1 Remember
Can principle component analysis viewed as unsupervised learning
10 BTL-3 Apply
algorithm? Examine.
11 Discuss about supervised learning algorithms. BTL-2 Understand
12 Give Venn diagram for Deep Learning. BTL-2 Understand
13 Specify the formula for conditional probability. BTL-6 Create
14 Illustrate support vector machine. BTL-3 Apply
15 Show the formula for Variance. BTL-3 Apply
16 Differentiate Independence and Conditional Independence. BTL-2 Understand
17 Analyze Eigen Decomposition. BTL-4 Analyze

18 Analyze random variable. BTL-4 Analyze

2
19 Probability theory is a fundamental tool of many disciplines of science BTL-5 Evaluate
and engineering. Justify.
20 Develop a formula for unbiased sample covariance matrix associated with BTL-6 Create
an m x n dimensional matrix X. Assume E[x] =0.
21 Analyze abouttensor. BTL-4 Analyze
22 Illustrate identity matrix? BTL-3 Apply
23 Discuss about matrix inverse. BTL-2 Understand
24 Assess linear dependence of vectors. BTL-5 Evaluate

PART – B
i. What is Deep Learning? (3)
1 ii. Describe how different parts of an Artificial Intelligence system relate BTL-1 Remember
to each other within different AI disciplines in detail with diagram.(10)
2 Describe how deep learning is a kind of representation learning with the BTL-1 Remember
Venn diagram. (13)
3 Listand explain the historical trends in Deep Learning. BTL-1 Remember

i. Discussabout scalars.(7)
4 BTL-2 Understand
ii. Give detail description of vectors. (6)
i. Give the Difference between deep learningand machine learning.(7)
5 BTL-2 Understand
ii. Give the various concepts of probability. (6)
6 i. Demonstrate linear dependence and independence of vectors.(7) BTL-3 Analyze
ii. Explainspan of vectors. (6)
7 Analyze and write short notes on the following. BTL-4 Analyze
i. Vectors. (6)
ii. Matrices.(7)
Explain the following in detail.
8 i. Eigen Decomposition. (7) BTL-4 Apply
ii. Tensors.(6)
9 Assess the following. BTL-5 Evaluate
i. Expectation .(5)
ii. Variance.(4)
iii. Covariance . (4)

Extrapolate conditional probability and Develop a summary of various

10 BTL-6 Create
common probability distribution. (13)
11 Describe Stochastic Gradient Descent. (13) BTL-1 Remember
12 i. Illustrate the importance of principal components analysis. (6) BTL-3 Analyze
ii. Explain support vector machines in detail. (7)
13 Explain supervised learning algorithm. (13) BTL-4 Apply

3
14 Discuss unsupervised learning algorithm. (13) BTL-2 Understand
15 Discuss Normal distribution. (13) BTL-2 Understand
16 Explain Probability Mass function and Probability Density function. (13) BTL-3 Analyze
17 Explain Principal Components Analysis. (13) BTL-5 Evaluate

PART – C
1 Develop short notes on followingwith respect to deep learning with BTL-6 Create
examples.
i) Scalar and Vectors. (6)
ii) Matrices. (7)
Assess the following with respect to deep learning examples.
2 i) Random Variables. (6) BTL-5 Evaluate
ii) Probability. (7)
3 Develop a supervised learning algorithm and explain in detail.(15) BTL-6 Create
4 Assess unsupervised learning algorithm.(15) BTL-5 Evaluate
5 Assess the historical developments in deep learning. (15) BTL-5 Evaluate

UNIT - II: DEEP NETWORKS

Deep Feed Forward Network: Learning XOR – Gradient Based Learning- Hidden Units – Architecture
Design – Back Propagation Algorithms. Regularization for Deep Learning: Parameter Norm Penalties –
Regularization and unconstrained Problems – Dataset Augmentation – Noise Robustness – Semi
supervised Learning – Challenges in Neural Network Optimization.

PART – A
Q. Questions BT Competence
No Level
1 Point out different set of layers in Feed forward networks. BTL-4 Analyze
2 Point out the default activation function for modern neural networks. BTL-4 Analyze
3 Compare linear models and neural networks. BTL-5 Evaluate
4 Develop three generalizations of rectified linear units based on using a BTL-6 Create
non-zero slope.
5 What is Deep Feed Forward networks? BTL-1 Remember
6 List reasonably common hidden unit types. BTL-1 Remember
7 Give the drawback of rectified linear units. BTL-2 Understand
8 Describe gradient descent. BTL-2 Understand
9 Give example of a feed forward neural network. BTL-2 Understand
10 Define chain rule of calculus. BTL-1 Remember
11 List some classification problems where Data augmentation is used. BTL-1 Remember
12 Define universal approximation theorem for feed forward network. BTL-1 Remember

4
13 What critical points or stationary points in derivative illustration of a BTL-1 Remember
function?
14 Describe regularization for deep learning. BTL-2 Understand
15 Illustrate semi supervised learning. BTL-3 Apply
16 Illustrate the derivative function used in gradient descent algorithm. BTL-3 Apply
17 Explain importance of dataset augmentation. BTL-3 Apply
18 Analyze and write chain rule of calculus. BTL-4 Analyze
19 Reason for calling Feedforward neural networks as networks–Justify. BTL-5 Evaluate
20 Develop a computational graph for any function. BTL-6 Create
21 Give reason for the term “feed forward” used in the feed forward BTL-2 Understand
networks.
22 Explain XOR operation. BTL-3 Apply
23 Analyze cost function. BTL-4 Analyze
24 Justify the application of Dataset Augmentation various tasks BTL-5 Evaluate

PART – B
1 Describe Deep feed forward networks. (13) BTL-1 Remember
2 Explain cost function ingradient based learning. (6) BTL-3 Apply
Explain learning conditional distributions with maximum likelihood. (7)
3 i. Describe about learning conditional statistics in gradient based BTL-1 Remember
learning.(7)
ii. Explain linear units for Gaussian Output Distributions.(6)
4 Explain output units of feed forward networks. (13) BTL-3 Apply
5 i. Explain sigmoid units for Bernoulli Output Distributions.(8) BTL-5 Evaluate
ii. Justify the importance of Rectified linear units in Hidden units. (5)
6 i. GiveSoftmax units for Multinoulli Output Distributions. (7) BTL-2 Understand
ii. Discuss about Hidden Units. (6)
7 i. Describe Rectified linear units and their generalizations. (7) BTL-2 Understand
ii. Describe Logistic Sigmoid and Hyperbolic Tangent. (6)

8 i. Write a short notes on Radial Basis function, Softplus and Hard tanh(7) BTL-4 Analyze
ii. Write a short notes on Architecture Design. (6)

9 i. Describe Back Propagation algorithm. (7) BTL-1 Remember

ii. Explain regularization for deep learning. (6)
10 Briefly describe Universal Approximation Properties and Depth. (13) BTL-1 Remember
11 Analyze and write short notes on Dataset Augmentation. (13) BTL-4 Analyze

12 Develop a data set and demonstrate Noise Robustness. (13) BTL-6 Create
13 Discuss in detail about chain rule of calculus. (13) BTL-2 Understand

5
 14 Illustrate Computational graphs. (13) BTL-4 Analyze
15 Give the applications of Dataset Augmentation. (13) BTL-2 Understand
16 Explain Multi-Task Learning. (13) BTL-3 Analyze
17 Assess Computational graphs with necessary diagrams. (13) BTL-5 Evaluate
PART – C
1 Develop a Deep Feed forward network and explain. (15) BTL-6 Create
Assess the routines to implement forward propagation computation.
2 BTL-5 Evaluate
(15)
3 Assess the difference between linear models and neural networks. (15) BTL-5 Evaluate
4 Develop your own scenarios to demonstrate computational graph. (15) BTL-6 Create
5 Develop Chain Rule of Calculus. (15) BTL-6 Create

UNIT - III: CONVOLUTIONAL NETWORKS

The Convolution Operation – Motivation – Pooling – Variants of the Basic Convolution Function – Structured Outputs
– Data types – Efficient Convolution Algorithm – Random or Unsupervised Features.
Q.N Questions BT Competence
o Level
PART – A
1 An essential feature of any convolutional network implementation is the
BTL-5 Evaluate
ability to implicitly zero-pad the input V.Justify
2 The output layer of convolutional network is usually relatively inexpensive
BTL-5 Evaluate
to learning layer. Justify.
3 What is convolutional networks? BTL-1 Remember
4 Createa chart that demonstrates convolution with a stride. BTL-6 Create
5 Howpooling handles inputs of varying size? BTL-4 Analyze
6 Whatis meant by convolution? BTL-1 Understand
7 List three important ideas that help to improve a machine learning system. BTL-1 Remember
8 Whatisunshared convolution? BTL-2 Understand
9 Defineprimary visual cortex. BTL-1 Remember
10 Howto reduce the cost of convolutional network training? BTL-2 Understand
11 Simulatethe idea behind reverse correlation. BTL-6 Create
12 Discussabout parameter sharing in neural network. BTL-2 Understand
13 Give three properties of V1 that a convolutional network layer is designed
BTL-2 Understand
to capture.
14 Explain feature map. BTL-4 Analyze
Explain how a convolutional layer have a property called equivariance to
15 BTL-3 Apply
translation?

6
16 List three stages of a convolutional network. BTL-1 Remember
17 List out various formats of data that can be used with convolutional BTL-1 Remember
networks.
18 Illustrate pooling stage in convolutional network. BTL-3 Apply
Differentiate complex layer terminology and simple layer terminology in
19 BTL-4 Analyze
convolutional network.
20 Show three basic strategies for obtaining convolution kernels without BTL-3 Apply
supervised training.
21 Give example for convolution. BTL-2 Understand
22 Illustrate reverse correlation. BTL-3 Apply
23 Explain complex layer terminology. BTL-4 Analyze
24 Examine equivariance to translation. BTL-5 Evaluate
PART – B
1 Write an example function for Convolution operation and explain in detail. BTL-1 Remember
(13)
2 Explain the following with suitable diagram. BTL-4 Analyze
i. Sparse interactions. (6)
ii. Parameter sharing. (7)
3 DescribePooling with suitable example. (13) BTL-1 Remember
4 Write an expression for Unshared convolution with explanation and BTL-1 Remember
explain Tiled convolution.(13)
5 Discuss in detail the variants of the Basic Convolution Function. (13) BTL-2 Understand
6 Constructanarchitecturethat show complex layer terminology and Simple BTL-5 Evaluate
layer terminology in convolutional neural network.
7 Discuss local connections, convolution and full connections with diagram? BTL-2 Understand
(13)
8 Developa table with examples of different formats of data that can be used BTL-6 Create
with convolutional networks. (13)
9 Describe in detail about the following. BTL-1 Remember
i. Parameter Sharing. (7)
ii. Equivariant representation. (6)
10 Differentiatelocally connected layers, tiled convolution and standard BTL-4 Analyze
convolution with suitable examples and diagram. (13)
11 i. Write short notes Max Pooling. (6) BTL-2 Remember
ii. Explain Pooling with downsampling. (7)
12 Explain random or Unsupervised Features.(13) BTL-4 Analyze
13 Illustrateunshared convolutionwith suitable examples. (13) BTL-3 Apply
14 i. Show three properties of V1 that a convolutional network layer is BTL-3 Apply
designed to capture. (6)
ii. Provethe working learned invariances with necessary example and
diagram. (7)
15 Discuss parameter sharing. (13) BTL-2 Understand

7
 16 IllustrateEquivariant representation. (13) BTL-3 Analyze
17 Evaluate the working learned invariances with necessary example and BTL-5 Evaluate
diagram. (13)
PART – C
1 Constructa graphical demonstration for sparse connectivity and explain it BTL-5 Evaluate
in detail. (15)
2 Create a graphical demonstration for parameter sharing and explain it in BTL-6 Create
detail. (15)
3 Evaluatevariants of the basic convolution function. (15) BTL-5 Evaluate
4 Construct a convolutional network to demonstrate the effect of zero BTL-6 Create
padding on network size.
Explain Neuro scientific basis for Convolutional Networks. (15)
5 Create a table with examples of different formats of data that can be used BTL-6 Create
with convolutional networks. (15)

UNIT - IV: SEQUENCE MODELING: RECURRENT AND RECURSIVE NETS

Unfolding Computational Graphs – Recurrent Neural Networks – Bidirectional RNNs – Encoder Decoder Sequence to
Sequence Architectures – Deep Recurrent Networks – Recursive Neural Networks – The Challenge of Long- Term
Dependencies – Echo State Networks – The Long-term memory and other Gated RNNs – Optimization for Long Term
Dependencies – Explicit Memory.

PART – A
Q.No Questions BT Competence
Level
1 What is Recurrent Neural Networks? BTL-1 Remember
2 What is Encoder? BTL-1 Remember
3 Give the blocks of decomposition of computation of most Recurrent Neural BTL-2 Understand
Networks.
4 What is Bidirectional Recurrent Neural Networks? BTL-1 Remember
5 Give the advantage of recursive nets over recurrent nets. BTL-2 Understand
6 What is decoder? BTL-1 Remember
7 Describe Recursive Neural Networks. BTL-1 Remember
8 Predict the concept of gated RNNs. BTL-2 Understand

8
9 Compare echo state network and liquid state machines. BTL-4 Analyze
10 Distinguish content based addressing and location based addressing in BTL-2 Understand
memory networks.
11 Classify the different strategies for Multiple Time Scales. BTL-3 Apply
12 Developa block diagram for LSTM. BTL-6 Create
13 Illustrateimportant design patterns for recurrent neural networks. BTL-3 Apply
14 Summarize about echo state networks. BTL-5 Evaluate
15 Point out the advantage of introducing depth in Deep recurrent Networks. BTL-4 Analyze
16 Compare gradient descent with and without gradient clipping using BTL-4 Analyze
diagram.
17 Justify the major advantages of unfolding process in computational BTL-5 Evaluate
graphs.
18 Illustrate block diagram of LSTM recurrent network “cell”. BTL-3 Apply
19 What are leaky units? BTL-1 Remember
20 Develop a schematic diagram of a network with an explicit memory. BTL-6 Create
21 Give a block diagram for Long Short Term Memory. BTL-2 Understand
22 Illustrate echo state networks. BTL-3 Apply
23 Explain liquid state machines. BTL-4 Analyze
24 Assess explicit memory. BTL-5 Evaluate
PART – B
1 i. Describe Unfolding Computational Graphs. (6) BTL-1 Remember
ii. Explain Bidirectional RNNs. (7)
2 Describe the following. BTL-1 Remember
i. Teacher Forcing in Recurrent Neural Networks. (7)
ii. Networks with Output Recurrence. (6)
3 i. Describe Echo State Networks. (7) BTL-1 Remember
ii. Explain challenge of Long-Term Dependencies.(6)
4 Discuss Recurrent Neural Networks in detail.(13) BTL-2 Understand
5 Describe Deep Recurrent Networks in detail.(13) BTL-2 Understand
6 Illustrate Encoder-Decoder sequence-to-sequence Architecture. (13) BTL-3 Apply
7 Explain Leaky Units and Other Strategies for Multiple Time Scales. (13) BTL-4 Analyze
8 Point out various features of Echo state networks. (13) BTL-4 Analyze
9 Explain Optimization for Long-Term Dependencies. (13) BTL-5 Evaluate
10 Compute the gradient in a Recurrent Neural Network. (13) BTL-6 Create

9
 11 i. Illustrate Clipping Gradients. (7) BTL-3 Apply
ii. Illustrate Regularizing to Encourage Information Flow.( 6)
12 Describe the following. BTL-1 Remember
i. Long Short-Term Memory. (7)
ii. Other Gated RNNs. (6)
13 Explain in detail about the following. BTL-4 Analyze
i. Adding Skip Connections through Time. (6)
ii. Leaky Units and a Spectrum of Different Time Scales .(7)
14 Describe Explicit memory. (13) BTL-2 Understand
15 Discuss Echo State Networks. (13) BTL-2 Understand
16 Illustrate Bidirectional RNNs.(13) BTL-3 Analyze
17 Explain challenge of Long-Term Dependencies. (13) BTL-5 Evaluate
PART – C
1 Develop an example for Unfolding Computational Graphs and describe the BTL-6 Create
major advantages of unfolding process. (15)
2 Explain how to compute the gradient in a Recurrent Neural Network.(15) BTL-5 Evaluate
3 Explain a modeling sequences Conditioned on Context with RNNs. (15) BTL-5 Evaluate
4 Prepare an example of Encoder- Decoder or sequence-to-sequence RNN BTL-6 Create
architecture.(15)
5 Explain variousGated RNNs. (15) BTL-5 Evaluate

UNIT - V: DEEP LEARNING APPLICATION

Linear Factor Models – Auto Encoders - Representation Learning – Structured Probabilistic Models for Deep
Learning - Monte Carlo Methods.
PART – A
Q.No Question BT Competence
Level
1 What is Probabilistic PCA and Factor Analysis? BTL-1 Remember
2 Define Linear Factor Model. BTL-1 Remember
3 Give the various generalizations of ICA. BTL-2 Understand
4 What is Independent Component Analysis? BTL-1 Remember
5 Give major advantage of slow feature analysis. BTL-2 Understand
6 Name the various tasks than can be done by probabilistic models. BTL-1 Remember
7 What is Denoising Autoencoders? BTL-1 Remember
8 Predict the primary disadvantage of the non-parametric encoder. BTL-2 Understand
9 Point out the trade-off faced in representation learning problems. BTL-4 Analyze

10
10 Distinguish between one-shot learning and zero-shot learning. BTL-2 Understand
11 Classify the different Graphical models. BTL-3 Apply
12 Develop distribution equation for energy based model. BTL-6 Create
13 Which areundirected models? BTL-3 Apply
14 Summarize Distributed representations. BTL-5 Evaluate
15 Point out the reason for why Greedy layer-wise pre-training called BTL-4 Analyze
Greedy.
16 Compare directed models and undirected models. BTL-4 Analyze
17 Slow Feature Analysis is an efficient application of slowness principle? BTL-5 Evaluate
Justify.
18 How many task does the learner must perform in transfer learning? BTL-3 Apply
19 List the two different ideas combined by Unsupervised pre-training. BTL-1 Remember
20 Develop an example fordistribution equation that represent a Boltzman BTL-6 Create
distribution.
21 Give an example of learning algorithm based on non-distributed BTL-2 Understand
representations.
22 Compare distributed representation and a symbolic one. BTL-4 Analyze
23 Illustrate the reasons for which Modeling a rich distribution is not feasible BTL-3 Apply
in unstructured modeling.
24 Evaluate Undirected models. BTL-5 Evaluate
PART – B
1 DescribeSparse Coding. (13) BTL-1 Remember
Describe the following
2  i. Probabilistic PCA and. (6) BTL-1 Remember
 ii. Factor Analysis. (7)
3 Describe the following. BTL-1 Remember
1. i, Independent Component Analysis,.(5)
ii, Slow Feature Analysis. (8)
4 DiscussManifold interpretation of PCA. (13) BTL-2 Understand
5 DiscussAutoencoders. (13) BTL-2 Understand
6 Write in detail about Undercomplete Autoencoders. (13) BTL-3 Apply
7 Explain Regularized Autoencoders. (13) BTL-4 Analyze
8 Compare Structured Probabilistic Model and Unstructured Modeling (13) BTL-4 Analyze
9 Summarizeusage of various Graphs to describe Model Structure.(13) BTL-5 Evaluate
10 Develop an example distribution equation for energy-based model and explain in BTL-6 Create
detail. (13)
11 i. Write short notes Sparse Autoencoders.(7) BTL-4 Analyze
ii. IllustrateDenoising Autoencoders. (6)
Describe the following.
12 i. Representation learning.(6) BTL-1 Remember
ii. Greedy Layer-Wise Unsupervised Pretraining.(7)

11
13 Discuss in detail about transfer learning and Domain Adaptation. (13) BTL-3 Apply
14 Describe Distributed Representation.(13) BTL-2 Understand
15 Discuss about Slow Feature Analysis. (13) BTL-2 Understand
16 Write about representation learning. (13) BTL-3 Analyze
17 Explain Markov random fields. (13) BTL-5 Evaluate

PART – C
1 Develop a short notes on Separation and D-Separation.(15) BTL-6 Create
2 ExplainMonte Carlo methods.(15) BTL-5 Evaluate
3 Explain Autoencoders.(15) BTL-5 Evaluate
4 Developa various graphs to describe Model Structure. (15) BTL-6 Create
5 AssessIndependent Component Analysis. (15) BTL-5 Evaluate

12