Format No. QSP/7.1/01.F01 (B) Issue No.05 Rev.

No 5 Dated: Jan 1, 2017

______________________________________________________________________
UNIVERSITY OF PETROLEUM & ENERGY STUDIES
School of Computer Science
Dehradun
COURSE PLAN

Program : B. Tech (CSE) –AIML

Course : Neural Networks
Course Code : CSAI 3101
No. of credits : 1
Semester :V
Session : 2022-23 (July - December. 2022)
Batch : 2019-23
Instructor : Javed Imran
Email : [email protected]

Approved By

_______________________ _______________________

Faculty HOD

UPES Campus Tel: +91-135-2770137

“Energy Acres” Fax: +91 135- 27760904
P.O. Bidholi, Via Prem Nagar, Dehradun Website: www.upes.ac.in
 COURSE PLAN
A. PREREQUISITE:

a. Basic Knowledge of statistics

b. Basic Knowledge of programming

B. PROGRAM OUTCOMES (POs)and PROGRAM SPECIFIC OUTCOMES (PSOs):

B1. PROGRAM OUTCOMES (POs)
PO1: Engineering knowledge: Apply the knowledge of mathematics, science, engineering
fundamentals, and an engineering specialization to the solution of complex engineering
problems.

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

PO3: Design/development of solutions: Design solutions for complex engineering 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 engineering and IT tools including prediction and modeling to complex engineering
activities with an understanding of the limitations.

PO6: The engineer 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 engineering practice.

PO7: Environment and sustainability: Understand the impact of the professional

engineering 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 engineering 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
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.

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

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.

B2. Program Specific Outcomes (PSOs)

PSO1: Perform system and application programming using computer system concepts,
concepts of Data Structures, algorithm development, problem solving and optimizing
techniques.

PSO2: Apply software development and project management methodologies using concepts
of front-end and back-end development and emerging technologies and platforms.

PSO3:Ability to create & develop most efficient solutions by applying machine learning with
analytical emphasis on industrial and research problems.

C. Course Outcomesfor Introduction to Machine Learning

Course Outcomes

CO1.To understand the concepts of pytorch framework.

CO2. To write pytorch script for neural network pipeline
CO3. 3. To implement different types of neural networks architectures for different applications.
 Table: Mapping of POs and PSOs v/s COs
P
P S
Course PO O PO PO PO PO PO PO PO PO PO PSO O PS
Outcomes 1 PO2 3 4 5 6 7 8 9 10 11 12 1 2 O3
CO1 1 2 1 1 2 2
CO2 1 1 1 2 2 2
CO3 1 2 1 2 2 2
Average 1 1.7 1 1.66 2 2

1=weak 2= moderate 3=strong

COURSE OUTLINE

Expt. No. Big Ideas/ Topics CO Modality

Experiment No 1 Introduction to Basic python CO1
F2F/e-lab
Experiment No 2 Introduction to pytorch CO1
F2F/e-lab
Experiment No 3 Building neural network from scratch CO1
F2F/e-lab
Experiment No 4 Building neural network Back- CO2
propagation F2F/e-lab

Experiment No 5 Implementation of Convolution neural CO2

networks F2F/e-lab

Experiment No 6 Implementation of RNN CO2

F2F/e-lab
Experiment No 7 Implementation LSTM CO2
F2F/e-lab
Experiment No 8 Implementation of GRU CO2
F2F/e-lab
Experiment No 9 Application of Image classification using CO2
CNN F2F/e-lab

Experiment No 10 Implementation of Generative CO3

adversarial networks F2F/e-lab
D. PEDAGOGY

a. Lab performance on Weka/Python

b. Assignments
c. Digital and analog Presentations
d. Lab File

E. COURSE COMPLETION PLAN

No. of No. of No .of Quiz No .of Quiz No. of No. of

experiments experiments planned conducted internal internal viva
planned completed viva conducted
planned
10 0 0 3 3

No. of lab classes per batch planned: 12 One Session =120 minutes

F. EVALUATION & GRADING

Description Weightage Schedule

1. Performance Records 50% During Lab Sessions
2. Viva Voce 50% One viva and quiz before mid-semester and
one viva and quiz after mid-semester

F1. Performance Records: Marks 100 (50% weightage)

10 Marks for each lab, consider marks of best 10 labs out of 12

Performance & Records 7 Marks
Lab File 3 Marks

Lab performance and record evaluation shall be a continuous process throughout the semester.

F2. Viva voce and Quiz: Marks 100 (50%)

 Viva 1: 20 Marks
 Viva 2: 25 Marks
  Internal assessment : 25 Marks
Conduct viva of 10 students in one lab session. So, one complete viva will be conducted in 3
Lab Sessions.

F3. GENERAL DISCIPLINE

Based on student’s regularity, punctuality, sincerity and participation in the
interactions. The marks obtained by the students will be displayed on LMS at the
end of semester.

F4. GRADING
The overall marks obtained at the end of the semester comprising all the above
two mentioned shall be converted to a grade. Students scoring less than 35
composite marks shall be awarded a ‘F’ grade. Students scoring 85 marks and
above as composite score shall be awarded a ‘O’ grade. The minimum individual
course grade is ‘C’.
The student who is debarred due to shortage of attendance for a lab course will
need to repeat the continuous evaluation during summer vacation (June-July) after
the registration by payment of the prescribed fee per subject as notified by the
University. The grades are awarded based on the performance of the students and
capping as per the University guidelines. All other rules and regulations such as
requirement of passing, etc. will remain same.

G. COURSE DELIVERY PLAN

Activities listed under ‘Lab activities’ should be performed F2F (face-to-face) in the
allocated laboratories (either compiled in lab machines or compiled online using e-labs).

Experiment No 1- Introduction to Python

Explore the tools with different options like

 Python installation
 Numpy array creation and manipulation
 Plots using matplotlib

Experiment No 2- Introduction to Pytorch

 Automatic differentiation
 Dataset creation
 Data loader
Experiment No 3- Building neural networks from scratch.

 Building a single layer perceptron without using any framework

Experiment No 4- Building neural network Back-propagation

 Building a multilayer perceptron and train using Backpropagation algorithm

Experiment No 5- Implementation of Convolution neural networks

 Demonstrate the implementation Conv, Pool, Activation, Fully connected layers

Experiment No 6-Implementation of RNN

 Program to demonstrate text classification using RNN

Experiment No 7- Implementation LSTM

 Program to demonstrate sentiment classification using LSTM

Experiment No 8-Implementation of GRU

 Perform to demonstrate human action recognition from sensor (Accelerometer,

gyroscope) data using GRU

Experiment No 9- Application of Image classification using CNN

 Program to demonstrate Covid detection using CNN.

Experiment No 10-Implementation of Generative adversarial networks

 Program to demonstrate style transfer using cyclic GAN

H. SUGGESTED READINGS:

H1. TEXT BOOK:

T1.Deep Learning with pytorch

I. GUIDELINES

Cell Phones and other Electronic Communication Devices: Cell phones and other electronic
communication devices (such as Blackberries/Laptops) are not permitted in classes during Tests or
the Mid/Final Examination. Such devices MUST be turned off in the class room.

E-Mail and online learning tool: Each student in the class should have an e-mail id and a pass
word to access the LMS system regularly. Regularly, important information – Date of conducting
class tests, guest lectures, via online learning tool. The best way to arrange meetings with us or ask
specific questions is by email and prior appointment. All the assignments preferably should be
uploaded on online learning tool. Various research papers/reference material will be
mailed/uploaded on online learning platform time to time.

Attendance: Students are required to have minimum attendance of 75% in each subject.
Students with less than said percentage shall NOT be allowed to appear in the end semester
examination.

Passing criterion: Student has to score total (Performance & Viva voce & Quiz) 35 marks.

J. COURSE OUTCOME ASSESSMENT

To assess the fulfilment of course outcomes two different approaches have been decided. Degree
of fulfillment of course outcomes will be assessed in different ways through direct assessment and
indirect assessment. In Direct Assessment, it is measured through quizzes, tests, assignment, Mid-
term and/or End-term examinations. It is suggested that each examination is designed in such a
way that it can address one or two outcomes (depending upon the course completion). Indirect
assessment is done through the student survey which needs to be designed by the faculty (sample
format is given below) and it shall be conducted towards the end of course completion. The
evaluation of the achievement of the Course Outcomes shall be done by analyzing the inputs
received through Direct and Indirect Assessments and then corrective actions suggested for further
improvement.
 NAME:

ENROLLMENT NO:

SAP ID:

COURSE: B. Tech. 3rdSemester

PROGRAM: CSE (GG)

Please rate the following aspects of course outcomes of Introduction to Machine Learning Lab
Use the scale 1-4*

Sr. No. Course Outcome 1 2 3 4

1 CO1 To discuss the basic concepts of model building and validation of
overall models
2 CO2. To experiment classification algorithm like Regression, Decision Trees,
K-NN, Neural Network etc.
3 CO3. To implement clustering algorithm like Hierarchical Clustering,
Partition based Clustering, Density based Clustering.

* 1 Below Average 3 Good

2 Average 4 Very Good