HKBK College of Engineering

Department of Computer Science and Engineering

SEMESTER – VI

DEEP LEARNING(21CS743)

Teaching Learning Plan

Course Code 21CS743 CIE Marks 50

Teaching Hours/Week (L:T:P: S) 0:4:0:0 SEE Marks 50
Total Hours of Pedagogy 50 Total Marks 100
Credits 04 Exam Hours 03

Course Facilitator: Dr. Sharada K, A

Pre-requisite: basic skills Machine Learning , Statistics, Linear Algebra

Programme Outcomes (POs) and Programme Specific Outcomes (PSOs)

1 Engineering Knowledge: Apply knowledge of mathematics, science, engineering fundamentals and an

engineering specialization to the solution of complex engineering problems.
2 Problem Analysis: Identify, formulate, research literature and analyze complex engineering problems
reaching substantiated conclusions using first principles of mathematics, natural sciences and
engineering sciences
3 Design/ Development of Solutions: Design solutions for complex engineering problems and design
system components or processes that meet specified needs with appropriate consideration for public
health and safety, cultural, societal and environmental considerations.
4 Conduct investigations of complex problems using research-based knowledge and research methods
including design of experiments, analysis and interpretation of data and synthesis of information to
provide valid conclusions.
5 Modern Tool Usage: Create, select and apply appropriate techniques, resources and modern
engineering and IT tools including prediction and modeling to complex engineering activities with an
under- standing of the limitations.
6 The Engineer and Society: Apply reasoning informed by contextual knowledge to assess societal,
health, safety, legal and cultural issues and the consequent responsibilities relevant to professional
engineering practice.
7 Environment and Sustainability: Understand the impact of professional engineering solutions in
societal and environmental contexts and demonstrate knowledge of and need for sustainable
development.
8 Ethics: Apply ethical principles and commit to professional ethics and responsibilities and norms of
engineering practice.
9 Individual and Team Work: Function effectively as an individual, and as a member or leader in
diverse teams and in multi disciplinary settings.
10 Communication: Communicate effectively on complex engineering activities with the engineering
community and with society at large, such as being able to comprehend and write effective reports and
design documentation, make effective presentations and give and receive clear instructions.
11 Life-long Learning: Recognize the need for and have the preparation and ability to engage in
independent and life- long learning in the broadest context of technological change.
 12 Project Management and Finance: Demonstrate knowledge and understanding of engineering and
management principles and apply these to one’s own work, as a member and leader in a team, to
manage projects and in multidisciplinary environments.
a. Problem-Solving Skills: An ability to investigate and solve a problem by analysis, interpretation of
data, design and implementation through appropriate techniques, tools and skills.
b. Professional Skills: An ability to apply algorithmic principles, computing skills and computer
science theory in the modeling and design of computer-based systems.
c. Entrepreneurial Ability: An ability to apply design, development principles and management skills
in the construction of software products of varying complexity to become an entrepreneur.

VI Semester:

DEEP LEARNING
Course Code 21CS743 CIE Marks 50
Teaching Hours/Week (L:T:P: S) 2:2:0:0 ,SEE Marks 50
Total Hours of Pedagogy 40, Total Marks 100
Credits 03, Exam Hours 03.

Course Objectives:
1. CLO 1. Understand the fundamentals of deep learning.
o

2. CLO 2. Know the theory behind Convolutional Neural Networks, Autoencoders, RNN.

3. CLO 3. . Illustrate the strength and weaknesses of many popular deep learning approaches

4. CLO 4. Introduce major deep learning algorithms, the problem settings, and their applications to
solve real world problems.

5. CLO 5. . Learn the open issues in deep learning, and have a grasp of the current research
directions.

Teaching-Learning Process (General Instructions)

These are sample Strategies, which teachers can use to accelerate the attainment of the various course
outcomes.

1. . Lecturer method (L) need not to be only a traditional lecture method, but alternative
effective teaching methods could be adopted to attain the outcomes.

2. Use of Video/Animation to explain functioning of various concepts.

3. Encourage collaborative (Group Learning) Learning in the class.

4. Ask at least three HOT (Higher order Thinking) questions in the class, which promotes
critical thinking.
5. Adopt Problem Based Learning (PBL), which fosters students’ Analytical skills, develop
design thinking skills such as the ability to design, evaluate, generalize, and analyze
information rather than simply recall it.
 6. Introduce Topics in manifold representations.
.
7. Show the different ways to solve the same problem with different circuits/logic and
encourage the students to come up with their own creative ways to solve them.

8. Discuss how every concept can be applied to the real world - and when that's possible, it
helps improve the students' understanding

Module-1
Introduction to Deep Learning: Introduction, Deep learning Model, Historical Trends in Deep
Learning,
Machine Learning Basics: Learning Algorithms, Supervised Learning Algorithms,
Unsupervised Learning Algorithms.
Textbook 1: Chapter1 – 1.1, 1.2, 5.1,5.7-5.8.
Teaching-Learning Process Chalk and board, Active Learning, Problem based learning

Teaching-Learning Process: Chalk and board, Active Learning, Problem based learning
Module-2
Feedforward Networks: Introduction to feedforward neural networks, Gradient-Based Learning,
Backpropagation and Other Differentiation Algorithms. Regularization for Deep Learning,
Textbook 1: Chapter 6, 7
Teaching-Learning Process Chalk and board, Active Learning, Demonstration

Teaching-Learning Process: Chalk and board, Active Learning, Demonstration

Module-3:
Optimization for Training Deep Models: Empirical Risk Minimization, Challenges in Neural Network
Optimization, Basic Algorithms: Stochastic Gradient Descent, Parameter Initialization Strategies,
Algorithms with Adaptive Learning Rates: The AdaGrad algorithm, The RMSProp algorithm,
Choosing
the Right Optimization Algorithm.
Textbook 1: Chapter: 8.1-8.5
Teaching-Learning Process Chalk and board, Problem based learning, Demonstration

Teaching-Learning Process: Chalk and board, Problem based learning, Demonstration

Module-4
Convolutional Networks: The Convolution Operation, Pooling, Convolution and Pooling as an
Infinitely
Strong Prior, Variants of the Basic Convolution Function, Structured Outputs, Data Types, Efficient
Convolution Algorithms, Random or Unsupervised Features- LeNet, AlexNet.
Textbook 1: Chapter: 9.1-9.9.
Teaching-Learning Process Chalk& board, Problem based learning

Teaching-Learning Process:
Chalk& board, Problem based learning

Module-5
Recurrent and Recursive Neural Networks: Unfolding Computational Graphs, Recurrent Neural
Network, Bidirectional RNNs, Deep Recurrent Networks, Recursive Neural Networks, The Long
short-term memory and Other Gated RNNs.
Applications: Large-Scale Deep Learning, Computer, Speech Recognition, Natural Language
 Processing
and Other Applications.
Textbook 1: Chapter: 10.1-10.3, 10.5, 10.6, 10.10, 12.
Teaching-Learning Process Chalk and board, MOOC

Teaching-Learning Process:
Chalk and board, MOOC

Course Outcomes (Course Skill Set)

At the end of the course the student will be able to:
Description Bloom’s
Sl. Course
Taxonomy
No. Outcome
Level
Understand the fundamental issues and challenges of deep
1. CO 1 learning data, model selection, model Understanding
complexity etc.,
(2)
2. Describe various knowledge on deep learning and algorithms Understanding
CO 2
(2)
Apply CNN and RNN model for real time applications
3. CO 3 Analyze (4)

Identify various challenges involved in designing and Understanding

4. CO4 implementing deep learning algorithms.
(2)

5. Relate the deep learning algorithms for the given types of

CO5 Analyze (4)
learning tasks in varied domain

Assessment Details (both CIE and SEE)

The weightage of Continuous Internal Evaluation (CIE) is 50% and for Semester End Exam (SEE)
is 50%.
The minimum passing mark for the CIE is 40% of the maximum marks (20 marks). A student shall
be deemed to have satisfied the academic requirements and earned the credits allotted to each
subject/course if the student secures not less than 35% (18 Marks out of 50) in the semester-end
examination (SEE), and a minimum of 40% (40 marks out of 100) in the sum total of the CIE
(Continuous Internal Evaluation) and SEE (Semester End Examination) taken together

Continuous Internal Evaluation:

Three Unit Tests each of 20 Marks (duration 01 hour)
1. First test at the end of 5th week of the semester
2. Second test at the end of the 10th week of the semester
3. Third test at the end of the 15th week of the semester
Two assignments each of 10 Marks
4. First assignment at the end of 4th week of the semester
5. Second assignment at the end of 9th week of the semester
Group discussion/Seminar/quiz any one of three suitably planned to attain the COs and POs for 20
Marks (duration 01 hours)
6. At the end of the 13th week of the semester
The sum of three tests, two assignments, and quiz/seminar/group discussion will be out of 100 marks
and will be scaled down to 50 marks
(to have less stressed CIE, the portion of the syllabus should not be common /repeated for any of the
methods of the CIE. Each method of CIE should have a different syllabus portion of the course).
CIE methods /question paper has to be designed to attain the different levels of Bloom’s
Taxonomy as per the outcome defined for the course.

CIE methods /question paper is designed to attain the different levels of Bloom’s taxonomy as per the
outcome defined for the course:
Assessment Details (both CIE and SEE)
The weightage of Continuous Internal Evaluation (CIE) is 50% and for Semester End Exam (SEE) is
50%.
The minimum passing mark for the CIE is 40% of the maximum marks (20 marks). A student shall be
deemed to have satisfied the academic requirements and earned the credits allotted to each subject/
course if the student secures not less than 35% (18 Marks out of 50) in the semester-end
examination
(SEE), and a minimum of 40% (40 marks out of 100) in the sum total of the CIE (Continuous Internal
Evaluation) and SEE (Semester End Examination) taken together
Continuous Internal Evaluation:
Three Unit Tests each of 20 Marks (duration 01 hour)
1. First test at the end of 5th week of the semester
2. Second test at the end of the 10th week of the semester
3. Third test at the end of the 15th week of the semester
Two assignments each of 10 Marks
4. First assignment at the end of 4th week of the semester
5. Second assignment at the end of 9th week of the semester
Group discussion/Seminar/quiz any one of three suitably planned to attain the COs and POs for 20
Marks (duration 01 hours)
6. At the end of the 13th week of the semester
The sum of three tests, two assignments, and quiz/seminar/group discussion will be out of 100
marks
and will be scaled down to 50 marks
(to have less stressed CIE, the portion of the syllabus should not be common /repeated for any of the
methods of the CIE. Each method of CIE should have a different syllabus portion of the course).
CIE methods /question paper has to be designed to attain the different levels of Bloom’s
taxonomy as per the outcome defined for the course
Semester End Examination:
Theory SEE will be conducted by University as per the scheduled timetable, with common question
papers for the subject (duration 03 hours)
1. The question paper will have ten questions. Each question is set for 20 marks. Marks scored shall
be proportionally reduced to 50 marks
2. There will be 2 questions from each module. Each of the two questions under a module (with a
maximum of 3 sub-questions), should have a mix of topics under that module.
The students have to answer 5 full questions, selecting one full question from each module
Suggested Learning Resources:
Textbooks

1. Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press, 2016.

Reference:
 Reference:
1. Bengio, Yoshua. "Learning deep architectures for AI." Foundations and trends in Machine
Learning, 2009.
2. N.D.Lewis, “Deep Learning Made Easy with R: A Gentle Introduction for Data Science”, January
2016.
3. Nikhil Buduma, “Fundamentals of Deep Learning: Designing Next-Generation Machine
Intelligence Algorithms”, O’Reilly publications.
Weblinks and Video Lectures (e-Resources):

Web links and Video Lectures (e-Resources):

● https://faculty.iitmandi.ac.in/~aditya/cs671/index.html
● https://nptel.ac.in/courses/106/106/106106184/
● https://www.youtube.com/watch?v=7x2YZhEj9Dw

Activity Based Learning (Suggested Activities in Class)/ Practical Based learning

Case study, Field visit

Google Drive:

Note: Drive Contents

1. Lesson Plan
2. Notes
3. PPTs
4. Text Books
5. Reference Books
6. Previous University QPs
7. Assignments
8. Question Banks

CO-PO/PSO Mapping:

PO- PO- PO- PO- PO- PO- PO- PO- PO- PO- PO- PO- PSO- PSO- PSO-
01 02 03 04 05 06 07 08 09 10 11 12 1 2 3

CO01 2 1 1 1 - 1 - - 1 - 1 - 1 2

CO02 2 1 1 - - - - - - - - - 1 2

CO03 2 1 1 - 2 - - - - - - 3 1 -

CO04 2 1 1 - - - - - 1 - - - 1 2

CO05 2 1 1 - - - - - - - - - 1 2

- - - - - - - - - - - - - -
AVG 2.00 1.00 1.00 1.00 2.00 1.00 - - 1.00 - 1.00 3.00 1.00 2.0 -
Session-Wise Plan:

M Se Topic C Reading Mode of Delivery Planned Executi

o ssi O s and Date on Date
d on Referen Synchro Asynchronous
u ces nous
l
e

Pedagog Pedagogy A
y s
s
e
s
s
m
e
n
t

PPT
Syllab and
us Discuss
copy ion:
Objecti Review
Introduction ves, of 20/9/20 20/9/20
1 1 Brainstorming
PPT-Induction 1 Outco prerequ 24 24
mes, isites
PEOs, and
POs, Course
PSOs Introdu
ction

a.Chalk
and
Text
Talk
Book https://youtu.be/
History of b.
1 2 1: VaRxMxKrKI4 23/9/24 23/9/24
Deep Learning Discuss
Chapte
ion
r 1.1

Increasing Text a.Chalk

DATA, Model Book and
1 3 Size, 1: Talk 24/9/24 24/9
Complexity Chapte b.Prese
And So on r 1.2 ntation

a.Chalk
Text
and https://youtu.be/
Overfitting and Book
Talk kbvHM2S2_bk
1 4 Underfitting 1: 27/9/24 26/9
b.
with capacity Chapte
Discuss
r 1.5
ion
 a.Chalk
Number of Text
and
Hidden Layers, Book https://youtu.be/tJmVf88l_ys
Talk
1 5 Number of 1: 30/9/24 30/9
b.
Neuron with Chapte
Discuss
years r 1.6
ion

a.Chalk
Text
and https://youtu.be/u5TAcNEJ-
Book
Supervised Talk xM
1 6 1: 1/10/24 1/10/24
Learning b.
Chapte
Discuss
r 2.1
ion

Unsupervised
Learning-
Clustering, https://youtu.be/D6gtZrsYi6c
Hierarchical Text a.Chalk
clustering, Book and https://youtu.be/yteYU_QpUxs
Distance 1: Talk 14/10/2
1 7 4/10/24
Based Chapte b. K Means Algorithm: 4
Clustering, K r 2.3 , Discuss https://youtu.be/
Means 2.3.1 ion CLKW6uWJtTc
Algorithm,
Outliers
identification

Text a.Chalk
Book and
Tutorial and 1: Talk 15/10/2
1 8 7/10/24
Quiz b. 4
Chapte Discuss
r 2.3.2 ion

https://youtu.be/jTzJ9zjC8nU
Introduction to
a.Chalk https://youtu.be/
Feed Forward Text
and eOtGPlAS6Yg?
neural Network Book
Talk si=h0QI7ziWtjSCvsbm 18/10/2
2 1 1: 8/10/24
b. 4
Feed Forward Chapte
Discuss
Computing r6
ion
Example

2 2 Gradient Text a.Chalk https://www.ibm.com/topics/ 21/10/2 14/10

Decent Book and gradient-descent 4
method: 1: Talk
Chapte b.
https://
Gradient r6 Discuss
towardsdatascience.com/
Decent ion
gradient-descent-algorithm-a-
Learning
deep-dive-cf04e8115f21
 https://youtu.be/
QZ8ieXZVjuE?
Text
Back a.Chalk si=7CPZIDRERbEfcQHW
1 Book
Propagation and 22/10/2
8 3 2 1: 14/10/2
2 Example: Talk https://youtu.be/ 4
Chapte
b. PPT GJXKOrqZauk
r6

Universal Text nalyticsvidhya.com/blog/

a.Chalk 2021/06/beginners-guide-to-
Approximation Book
and universal-approximation- 25/10/2
2 4 2 1: 18/21/24
theorem and Talk theorem/ 4
Chapte
Proof b. PPT
r6

Regularisation Text https://www.turing.com/kb/

a.Chalk
definition, and Book ultimate-guidebook-for-
and 28/10/2
2 5 types. L1 and 2 1: 21/10/24
Talk regularization-techniques-in- 4
L2 Chapte
b. PPT deep-learning
Regularisation r7

Text https://www.turing.com/kb/
a.Chalk
Regularisation Book ultimate-guidebook-for-
and 29/10/2
2 6 -Drop 2 1: 22/10/24
Talk regularization-techniques-in- 4
out(Bagging) Chapte
b. PPT deep-learning
r .7

Text
a.Chalk https://www.datacamp.com/
Regularization Book
and tutorial/complete-guide-data-
2 7 – Data 2 1: 8/11/24 25/10/24
Talk
Augumentation Chapte augmentation
b. PPT
r7

Text https://
a.Chalk
Different types Book www.geeksforgeeks.org/what-
and 11/11/2
2 8 of Batch 2 1: 11/11/24
Talk is-batch-normalization-in- 4
Normalization Chapte
b. PPT deep-learning/
r7

Text
a.Chalk
Book https://youtu.be/
Empirical Risk and 12/11/2
3 1 2 1: 12/11
Minimization Talk zAsgRxMXeZM 4
Chapte
b. PPT
r 8.1
 https://youtu.be/
NE88eqLngkg?
What is si=OsL_TAAW2mpBRWbU
Text
optimizer and a.Chalk
Book
GD, SGD, and or 15/11/2
3 2 2 1: 15/11
Mini Batch Talk 4
Chapte https://youtu.be/
Adagrad b. PPT
r 8.2 TudQZtgpoHk?
optimizers
si=v0ywxEdMlSxkcN20

RMS PROP:
https://youtu.be/wc5Qcv17w-
Q?si=REwJ-btGv4iK_N_X
ADAGRAD:
https://youtu.be/
GSmW59dM0-o?
ADA GRAD ,
si=cu0EmyaEKgppu8a4
RMS Prop, Text
a.Chalk
Book 1: ADAM Optimizers 19/11/2
3 3 ADAdelta and 3 and Talk 19/11
Chapter https://youtu.be/tuU59-G1PgU 4
ADAM b. PPT
8.3-8.5
Optimizers
All Optimizers:
https://youtu.be/
M2xkmc2oHUc?
si=OeBpPv4uMOnycqJE

Text ADAGRAD:
a.Chalk https://youtu.be/
Book
ADAGRAD and GSmW59dM0-o? 22/11/2
3 4 3 1: 25/11
optimizers Talk 4
Chapte si=cu0EmyaEKgppu8a4
b. PPT
8.3-8.5

ADAM Optimizers
https://youtu.be/tuU59-G1PgU
ADAM Text
a.Chalk
Book 1: 25/11/2
3 5 Optimizers 3
Chapter
and Talk All Optimizers: 29/11
b. PPT 4
8.3-8.5 https://youtu.be/
M2xkmc2oHUc?
si=OeBpPv4uMOnycqJE

All Optimizers:
All optimizers Text
a.Chalk https://youtu.be/
Book 1:
3 6 with 3
Chapter
and Talk 26/11/24 3/12
b. PPT M2xkmc2oHUc?
algorithms 8.3-8.5
si=OeBpPv4uMOnycqJE
 Choosing
Text https://fastercapital.com/
the Right a.Chalk
Book 1: topics/choosing-the-right-
3 7 Optimization 3 and Talk 29/11/24 6/12
Chapter optimization-algorithm.html
Algorithm. 4.2
b. PPT

https://youtu.be/
gLwX3zHkims?
CNN: Text si=77DI4vnYJT1o9DeH
a.Chalk
Book 1:
4 1 Convolution 3
Chapter
and Talk 2/12/24 9/12
operation b. PPT https://youtu.be/Etksi-F5ug8?
9
si=Qd5hTLCE1y56n7r4

https://youtu.be/
Text VpSLtKiPhLM?
a.Chalk
Pooling, Book 1:
4 2 3 and Talk si=dQqRUDWLfXdf5ST9 3/12/24 10/12
Convolution Chapter
b. PPT
9

https://youtu.be/lxk_nmpqI5M?
Filters, si=lC-UpMyw6riVJp19
Strides, Text
a.Chalk
4 3
pooling( Min 3
Book 1:
and Talk
Pooling:
6/12/24 11/12
and average Chapter
b. PPT
https://youtu.be/
pooling. 9 PGBop7Ka9AU?
si=CDGUyB7V6nPhQ6zn

https://www.google.com/
search?
q=Pooling+as+an+Infinitely+St
rong+Prior+video+lecture&rlz=
1C1CHBF_enIN1128IN1128&
oq=Pooling+as+an+Infinitely+
Text
Pooling as an a.Chalk +Strong+Prior+video+lecture&
Book 1:
4 4 Infinitely Strong 3 and Talk gs_lcrp=EgZjaHJvbWUyBggA 13/12/24 13/12
Chapter
Prior b. PPT EEUYOTIJCAEQIRgKGKABM
9
gcIAhAhGI8C0gEKMTEyNjBq
MGoxNagCCLACAQ&sourcei
d=chrome&ie=UTF-
8#fpstate=ive&vld=cid:daeac1
16,vid:R_AvSQJX1bs,st:0

Text https://youtu.be/aLjpU-ahEhA?
CNN and ANN a.Chalk
Book 1: si=-pTc3cjK30dELzqQ
4 5 difference: 3
Chapter
and Talk 16/12/24 14/12
b. PPT
9
 CNN with
kernals,
Pooling ,
Padding, Text a.Chalk https://youtu.be/Y1qxI-Df4Lk?
Flattening, Book 1: and Talk
4 6 3 si=4s7MpA4Ij4O4dF_N(CNN 17/12/24 17/12
Fully Chapter b.Discuss
Connected 9 ion
Neural
Network)

https://deep-learning-study-
note.readthedocs.io/en/
latest/Part%202%20(Modern
Text a.Chalk %20Practical%20Deep
Structured Book 1: and Talk %20Networks)/
4 7 3 20/12/24 18/12
output: Chapter b.Discuss 9%20Convolutional
9 ion %20Networks/
9.6%20Structured
%20Output.html

Text a.Chalk
https://youtu.be/lWPkNkShNbo Special Special
Why RNN in Book 1: and Talk
5 1 3 Online Online
Deep Learning Chapter b.Discuss
Classes Classes
10 ion

Unfolding
Computational Text a.Chalk https://youtu.be/ Special Special
Graphs, Book 1: and Talk
5 2 3 7ZQgK_MV_t0? Online Online
Recurrent Chapter b.Discuss
Classes Classes
10 ion si=D4MyF6JJrL3mNuwD
Neural
Network

https://youtu.be/

m_0axqxL-5I?

Text a.Chalk si=ka5D1fLwm7SuS7W

Special Special
Bidirectional Book 1: and Talk
5 3 3 h Online Online
RNNs Chapter b.Discuss
Classes Classes
10 ion
 DEEP RNN and
Text a.Chalk https://youtu.be/
Back Special Special
Book 1: and Talk Wu9BsMSKqyk?
5 4 Propagation 3 Online Online
Chapter b.Discuss si=OxPNb__o_G8XBMcI Classes Classes
through Time 10 ion
Steps

https://youtu.be/
rdkIOM78ZPk?
The Long
si=ehJeLIYqhzwoiHVS
Short Term Text a.Chalk
Special Special
Memory, Book : and Talk
5 5 3 Or Online Online
Advantages Chapter b.Discuss
Classes Classes
10 ion https://youtu.be/
and
VJHWOO2Ix_8?
Disadvantages
si=afccLjuihhLZkHNQ

Text a.Chalk
Special Special
Gated RNNs. Book 1: and Talk
5 6 3 https://youtu.be/ Online Online
Chapter b.Discuss
Classes Classes
10 ion
IBs8D8PWMc8

Applications: Text a.Chalk

Special Special
Large-Scale Book 1: and Talk https://youtu.be/kNuA2wflygM
5 07 4 Online Online
Deep Learning, Chapter b.Discuss
Classes Classes
Computer 12 ion

Applications of
Speech Text a.Chalk
https://youtu.be/m_0axqxL-5I Special Special
Recognition, Book 1: and Talk
5 08 4 Online Online
Natural Chapter b.Discuss https://youtu.be/V8qrVleGY5U
Classes Classes
Language 12 ion
Processing

Assessment Scheme: CIE:SEE 50:50

Sl. Assessment Frequency Weightage (%)

No. Instrument
1. Internal Assessment 3 3x20=60/3=20
2. Assignment and Quiz 2 2x10=20/2=10
3. GD/Seminar/Quiz 1 1x20=20
Total CIE 100 (reduced to 50)
4. End Semester Examination (UE) 1 50
Total 100