LAB MANUAL

DEEP LEARNING

SCHOOL OF COMPUTING SCIENCE &

ENGINEERING

COMPUTER SCIENCE & ENGINEERING

2023-2024
 SUBJECT Deep Learning PROGRAMME B. Tech.

SUBJECT CODE BTCS9608 SEMESTER 7

DURATION OF
CREDITS 3+1 13 Weeks
SEMESTER
PREREQUISITE SESSION
Machine Learning, Python 3 + 2 Hrs per Week
SUBJECTS DURATION

Vision
To be recognized globally as a premier School of Computing Science and Engineering for
imparting quality and value based education within a multi-disciplinary and collaborative
research based environment.

Mission
The mission of the school is to:

M1: Develop a strong foundation in fundamentals of computing science and engineering with
responsiveness towards emerging technologies.

M2: Establish state-of-the-art facilities and adopt education 4.0 practices to analyze, develop, test and
deploy sustainable ethical IT solutions by involving multiple stakeholders.

M3: Foster multidisciplinary collaborative research in association with academia and industry through
focused research groups, Centre of Excellence, and Industry Oriented R&D Labs.

PROGRAM EDUCATIONAL OBJECTIVES

The Graduates of Computer Science and Engineering shall:
PEO1: be engaged with leading Global Software Services and Product development
companies handling projects in cutting edge technologies.

PEO2: serve in technical or managerial roles at Government firms, Corporates and contributing to
thesociety as successful entrepreneurs through startup.

PEO3: undertake higher education, research or academia at institutions of transnational reputation.

PROGRAMME SPECIFIC OUTCOME (PSO)
The students of Computer Science and Engineering shall:

PSO1: Have the ability to work with emerging technologies in computing requisite to Industry 4.0.

PSO2: Demonstrate Engineering Practice learned through industry internship and research project
to solve live problems in various domains.

PROGRAMME OUTCOME (PO)

PO1 Computing Science knowledge: Apply the knowledge of mathematics, statistics, computing
science and information science fundamentals to the solution of complex computer application
problems.

PO2 Problem analysis: Identify, formulate, review research literature, and analyze complex
computing science problems reaching substantiated conclusions using first principles of mathematics,
natural sciences, and computer sciences.

PO3 Design/development of solutions: Design solutions for complex computing problems and
design system components or processes that meet the specified needs with appropriate consideration
for the public health and safety, and the cultural, societal, and environmental considerations.

PO4 Conduct investigations of complex problems: Use research-based knowledge and research
methods including design of experiments, analysis and interpretation of data, and synthesis of the
information to provide valid conclusions.
PO5 Modern tool usage: Create, select, and apply appropriate techniques, resources, and modern
computing science and IT tools including prediction and modeling to complex computin g activities
with an understanding of the limitations.

PO6 IT specialist and society: Apply reasoning informed by the contextual knowledge to assess
societal, health, safety, legal and cultural issues and the consequent responsibilities relevant to the
professional computing science and information science practice.

PO7 Environment and sustainability: Understand the impact of the professional computing science
solutions in societal and environmental contexts, and demonstrate the knowledge of, and need for
sustainable development.

PO8 Ethics: Apply ethical principles and commit to professional ethics and responsibilities and norms
of the computing science practice.

PO9 Individual and team work: Function effectively as an individual, and as a member or leader in
diverse teams, and in multidisciplinary settings.
PO10 Communication: Communicate effectively on complex engineering activities with the IT
analyst 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.

PO11 Project management and finance: Demonstrate knowledge and understanding of the
computing science 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.

PO12 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.
COURSE OBJECTIVE
 To understand the fundamentals of neural networks.
 To apply the concept of neural network in real-time use of deep learning.
 To apply the basic concept of deep learning in the implementation of convolutional
neural network over various datasets.
 To implement various automatic model of Deep Learning neural networks and evaluate
their performance.

COURSE OUTCOMES(COs)
After the completion of the course, the student will be able to:
CO No. Course Outcomes
608.1 Understand the fundamentals of Neural Networks.
608.2 Apply the concepts of Neural Networks in the development of deep learning models.
608.3 Analyze the deep learning models like RNN, CNN and LSTM.
608.4 Develop CNN, RNN and LSTM models and evaluate their performance.

BLOOM’S LEVEL OF THE COURSE OUTCOMES

Remember Understand Apply Analyse Evaluate Create

CO No.
KL1 KL 2 KL 3 KL 4 KL 5 KL 6
608.1 √ √
608.2 √
608.3 √
608.4 √ √

COURSE ARTICULATION MATRIX

The Course articulation matrix indicates the correlation between Course Outcomes and Program
Outcomes and their expected strength of mapping in three levels (low, medium, and high).
PSO1

PSO2
PO10

PO11

PO12
PO1

PO2

PO3

PO4

PO5

PO6

PO7

PO8

PO9

COs#/ POs

608.1 1

608.2 3 1 1

608.3 3 3 2

608.4 3 2 3

Note: 1-Low, 2-Medium, 3-High

 COURSE ASSESSMENT
The course assessment patterns are the assessment tools used both in formative and summative examinations.

CIE
Assessment
QUIZ1 CAT QUIZ2 LAB Course-
Tools CAT Total CIE
LAB based
/AAT 1 AAT 2 EXAM marks
Project SEE
--- X --- X X X
Integrated
0 30 0 30 20 20 0 100 100

Rubrics for Practical IA

S. No. Rubrics - Parts Marks

1 Performance 4

2 Result 6

3 File 4

4 Viva 6

Total 20
 List of Programs

S. N. Title of Lab Experiments

Python Programming Fundamental Revision: Python program to find sum, and percentage
1 from 5 subject marks out of 50.
2 Python program for working on Data Visualization.

3 Data Pre-processing using Linear Regression

Python program to implement k-Nearest Neighbor algorithm to classify the iris dataset. Print
4 both correct and wrong predictions.
Python program to implement the non-parametric locally weighted regression algorithm in
5 order to fit the data point. Select the appropriate data set for your experiment and draw
graphs.
Python program to build a machine learning model which will predict whether or not it will
6 rain tomorrow by studying past data.
7 Python program to implement AND, OR gates using perceptron.

8 Python program for classification of an XOR problem with multi-layer perceptron.

9 Python program to implement classification linearly separable data with perceptron.

10 Python program to recognize handwritten digits using neural network.

Python program to study a bank credit data set and determine whether a transaction is
11 fraudulent or not based on past data.
12 Python program for implementation of CNN.

13 Python program for implementation of RNN.

14 Python program for implementation of LSTM.

Value Added List of Experiments

1. Image Classification using CNN
2. Python program for implementation of Bidirectional LSTM.
3. Python program for implementation of Bidirectional RNN.

Name of the Course Lead: Dr. Abdul Aleem Signature