VII

BIKANER TECHNICAL UNIVERSITY, BIKANER
बीकानेरतकनीकीविश्वविद्यालय,बीकानेर
OFFICE OF THE DEAN ACADEMICS
SCHEME & SYLLABUS OF

UNDERGRADUATE DEGREE COURSE
of
B. Tech. (Computer Science and Engineering)
VII & VIII Semester
[Draft Syllabus Subjected to approval]
Effective for the students admitted in year 2021-22 and onwards

Approved by ……. academic council meeting held on …….
Approved by …….. academic council meeting held on ……….

Office: Bikaner Technical University, Bikaner
Karni Industrial Area, Pugal Road, Bikaner-334004; Website:https://btu.ac.in Page 1
Teaching & Examination Scheme

4rdYear – VII Semester
(Effective for the students admitted in year 2021-22 and onward)
S. No. Category Course Course Title Hours Exam Marks Credit
Code Hours
L T P IA ETE Total
THEORY
1 DC 7CS4-01 Deep Learning 3 - - 3 30 70 100 3
2 UE University Elective subject 3 - - 3 30 70 100 3
Course code and title to be selected
from the university elective pool
of subjects
3 7CS 5-11 Mobile Computing 2 - - 3 30 70 100 2
DE 7CS5-12 Soft Computing and
Evolutionary Algorithms
7CS5-13 Generative AI
Sub Total 8 00 00 - 90 210 300 8
PRACTICAL & SESSIONAL
4 DC 7CS4-21 Deep Learning Lab - - 2 - 60 40 100 1
5 UI 7CS7-30 Industrial Training - - 1 - 60 40 100 3
UI 7CS7-50 B.Tech. Project - I - - 3 - 60 40 100 2
6 CCA 7CS8-00 SODECA / Co-Curricular - - - - - 100 100 1
Activity
Sub Total 00 00 06 - 180 220 400 7
Total 8 00 06 - 270 430 700 15
L = Lecture, T = Tutorial, P = Practical, IA=Internal Assessment, ETE=End TermExam,Cr=Credits

Teaching & Examination Scheme

4rdYear – VIII Semester
(Effective for the students admitted in year 2021-22 and onward)
S. No. Category Course Course Title Hours Exam Marks Credit
Code Hours
L T P IA ETE Total
THEORY
1 UE University Elective subject 3 - - 3 30 70 100 3
Course code and title to be selected
from the university elective pool
of subjects
Sub Total 3 00 00 30 70 100 3
PRACTICAL & SESSIONAL
10 UI 8CS7-40 Seminar - - 2 - 60 40 100 2
UI 8CS7-50 B.Tech. Project - II - - 3 - 60 40 100 4
12 CCA 8CS8-00 SODECA / Co-Curricular - - - - - 100 100 2

Activity
Sub Total 00 00 05 - 120 180 300 8
Total 03 00 05 - 150 250 400 11
L = Lecture, T = Tutorial, = Practical, IA=Internal Assessment, ETE=End Term Exam,Cr=Credits

VII Semester
7CS4-01: Deep Learning
Credit: 3 Max. Marks: 100 ( IA:30, ETE:70)
3L+0T+ 0P End Term Exams: 3 Hours
Course Objectives:
As a result of successfully completing this course, students will be able :
• To describe the major differences between deep learning and other types of machine learning algorithms.
• To explain the fundamental methods involved in deep learning.
• To understand various aspects of deep learning and its building block.
• To understand and differentiate between the major types of neural network architectures.
• To Select or design neural network architectures for new data problems based on their requirements and
problem characteristics and analyze their performance.
• To understand basic working principles and how Deep Learning is used to solve real-world problems
Course Outcomes:
Upon successful completion of the course the students will be able to
CO-1: Able to learn the fundamental concepts of neural networks and deep neural networks.
CO-2: Able to understand the working principle of convolution neural networks.
CO-3: Able to perform hyperparameter tuning.
CO-4: Able to analyze and design neural network for real work problem. CO-5: Able to understand working
principle of various types of neural networks.
S. No. Contents Hours
1 Introduction to Neural Networks Introduction of artificial neural network and deep learning, 7
characteristics of neural networks terminology, neurons, perceptron, backpropagation, Basic
learning laws, Activation and Loss function - Function approximation, applications
2 Introduction to Convolution Neural Networks CNN Architecture and Operations, 8
convolutional layer, Pooling layer, Variants of the Convolution Model, Forward and Backward
propagation, Building a Deep Neural Network
Improving Deep Neural Networks Training a deep neural network, hyper-parameter tuning,
Hidden layers, Generalization Gap – Under-fitting Vs Over-fitting – Optimization,
Normalization
3 Practical aspects of Deep Learning: Train/Dev / Test sets, Bias/variance, Overfitting and 8
regularization, Linear models and optimization, Vanishing/exploding gradients, Gradient
checking – Logistic Regression, Convolution Neural Networks, RNN and Backpropagation –
Convolutions and Pooling
4 Optimization algorithms: Mini-batch gradient descent, exponentially weighted averages, 8
RMS prop, Learning rate decay, the problem of local optima, Batch norm – Parameter tuning
process
5 Neural Network Architectures: Recurrent Neural Networks, Adversarial NN, Spectral CNN, 9
Self-Organizing Maps, Restricted Boltzmann Machines, Long Short-Term Memory Networks
(LSTM) and Deep Reinforcement Learning – Tensor Flow, Keras or MatConvNet for
implementation.
Total 40
Suggested Books:
1. Deep Learning, Ian Goodfellow Yoshua Bengio Aaron Courville, MIT Press, 2017 (link
https://www.deeplearningbook.org/)
2. Deep Learning Step by Step with Python, N D Lewis, 2016
3. Deep Learning: A Practitioner's Approach, Josh Patterson, Adam Gibson, O'Reilly Media, 2017
4. Deep Learning, Ian Goodfellow Yoshua Bengio Aaron Courville, MIT Press, 2017
5. James Allen “Natural Language Understanding”, Pearson Publication 8th Edition. 2012.
6. François Chollet “Deep Learning with Python,” First Edition, Manning Publication,2018
7. Neural Networks and Deep Learning, Michael Nielsen, Determination Press (2015) (link:
http://neuralnetworksanddeeplearning.com/ )


VII Semester
7CS5-11: Mobile Computing
Course Objectives:
As a result of successfully completing this course, students will:
• To make the student understand the concept of the mobile computing paradigm, its novel applications, and
limitations.
• To understand the typical mobile networking infrastructure through a popular GSM protocol
• Understand the issues and solutions of various layers of mobile networks, namely MAC layer, Network Layer
& Transport Layer
• To understand the database issues in mobile environments & data delivery models.
• Understand the ad hoc networks and related concepts.
• To understand the platforms and protocols used in the mobile environment.
Course Outcomes:
Upon successful completion of the course, students will be able to
CO-1: Think and develop a new mobile application.
CO-2: Take any new technical issue related to this new paradigm and come up with a solution(s).
CO-3: Develop new ad hoc network applications and/or algorithms/protocols.
CO-4: Understand & develop any existing or new protocol related to the mobile environment
1 Introduction: Mobile Communications, Mobile Computing – Paradigm, Promises/Novel 5
Applications and Impediments and Architecture; Mobile and Handheld Devices, Limitations
of Mobile and Handheld Devices. GSM – Services, System Architecture, Radio Interfaces,
Protocols, Localization, Calling, Handover, Security, New Data Services, GPRS
2 (Wireless) Medium Access Control (MAC): Motivation for a specialized MAC (Hidden and 6
exposed terminals, Near and far terminals), SDMA, FDMA, TDMA, CDMA, Wireless
LAN/(IEEE 802.11)
3 Mobile Network Layer: IP and Mobile IP Network Layers, Packet Delivery and Handover 6
Management, Location Management, Registration, Tunneling and Encapsulation, Route
Optimization, DHCP
4 Mobile Transport Layer: Conventional TCP/IP Protocols, Indirect TCP, Snooping TCP, 6
Mobile TCP, Other Transport Layer Protocols for Mobile Networks. Database Issues: Database
Hoarding & Caching Techniques, Client-Server Computing & Adaptation, Transactional
Models, Query processing
5 Data Dissemination and Synchronization: Communications Asymmetry, Classification of 5
Data Delivery Mechanisms, Data Dissemination, Broadcast Models, Selective Tuning and
Indexing Methods, Data Synchronization – Introduction, Software, and Protocols.
Total 28
Suggested Books:
1. Jochen Schiller, “Mobile Communications”, Addison-Wesley, Second Edition, 2009.
2. Raj Kamal, “Mobile Computing”, Oxford University Press, 2007, ISBN: 0195686772
3. ASOKE K TALUKDER, HASAN AHMED, ROOPA R YAVAGAL, “Mobile Computing, Technology
Applications and Service Creation” Second Edition, Mc Graw Hill.
4. UWE Hansmann, Lother Merk, Martin S. Nicklaus, Thomas Stober, “Principles of Mobile Computing,”
Second Edition, Springer.

5. “GENESIS : Personal Communication Device”. GENESIS 191A321 Document, 1993.

6. “Intelligent Vehicle Highway Systems Projects”. Department of Transportation, Minnesota Document,
March 1994.

VII Semester
7CS5-12: Soft Computing and Evolutionary Algorithms
Course Objectives:
• Able to understand basics of Fuzzy Set
• Able to understand the concepts of the genetic algorithms.
• Able to understand the idea of the evolutionary algorithms.
Course Outcomes:
CO-1: Comprehend the fuzzy logic and the concept of fuzziness involved in various systems and fuzzy set
theory.
CO-2: Understand the concepts of fuzzy sets, knowledge representation using fuzzy rules, approximate
reasoning, fuzzy inference systems, and fuzzy logic
CO-3: Describe with genetic algorithms and other random search procedures useful while seeking global
optimum in self learning situations.
CO-4: Develop some familiarity with current research problems and research methods in Soft Computing
Techniques
1 Introduction to Soft Computing: Aims of Soft Computing-Foundations of Fuzzy Sets 5
Theory-Basic Concepts and Properties of Fuzzy Sets- Elements of Fuzzy Mathematics-Fuzzy
Relations-Fuzzy Logic
2 Application of Fuzzy Sets: Applications of Fuzzy Sets-Fuzzy Modeling – Fuzzy Decision 6
Making-Pattern Analysis and Classification-Fuzzy Control Systems-Fuzzy Information
Processing- Fuzzy Robotics.
3 Genetic Algorithms: Main Operators- Genetic Algorithm Based Optimization-Principle of 6
Genetic Algorithm- Genetic Algorithm with Directed Mutation- Comparison of Conventional
and Genetic Search Algorithms Issues of GA in practical implementation. Introduction to
Particle swarm optimization-PSO operators-GA and PSO in engineering applications
4 Neuro-Fuzzy Technology: Fuzzy Neural Networks and their learning-Architecture of Neuro- 6
Fuzzy Systems- Generation of Fuzzy Rules and membership functions - Fuzzification and
Defuzzyfication in Neuro-Fuzzy Systems- Neuro-Fuzzy Identification - Neuro Fuzzy Control-
Combination of Genetic Algorithm with Neural Networks- Combination of Genetic
Algorithms and Fuzzy Logic-Neuro-Fuzzy and Genetic Approach in engineering applications.
5 Basic Evolutionary Processes, EV: A Simple Evolutionary System, Evolutionary Systems as 5
Problem Solvers, A Historical Perspective, Canonical Evolutionary Algorithms - Evolutionary
Programming, Evolution Strategies, A Unified View of Simple EAs- A Common Framework,
Population Size
Total 28
Suggested Books:
1. An Introduction to Genetic Algorithm Melanic Mitchell (MIT Press)
2. Evolutionary Algorithm for Solving Multi-objective, Optimization Problems (2nd Edition), Collelo,
Lament, Veldhnizer ( Springer)
3. Fuzzy Logic with Engineering Applications Timothy J. Ross (Wiley)
4. Sivanandam, Deepa, “ Principles of Soft Computing”, Wiley

5. Jang J.S.R, Sun C.T. and Mizutani E, "Neuro-Fuzzy and Soft computing", Prentice Hall
6. Timothy J. Ross, "Fuzzy Logic with Engineering Applications", McGraw Hill

VII Semester
7CS5-13: Generative AI
Course Objectives:
As a result of successfully completing this course, students will be:
• Understand the fundamentals of generative AI and its applications in computer vision and natural
language processing.
• Develop skills in designing and implementing generative models using deep learning frameworks.
• Analyze and evaluate the performance of generative models in various applications.
Course Outcomes:
CO-1: Design and implement generative models for image and text generation, and other applications.
CO-2: Understand the strengths and limitations of various generative models and be able to select appropriate
models for specific tasks.
CO-3: Develop problem-solving skills using generative AI and be able to apply them to real-world problems.
CO-4: Critically evaluate the performance of generative models and develop strategies for improvement.
1 Introduction: Objective, scope and outcome of the course 1
2 Overview of Generative AI: Types of Generative Models (VAE, GAN, RNN, etc.), 6
Applications of Generative AI (Image Generation, Text Generation, etc.)
3 Generative Models for Computer Vision : Convolutional Neural Networks (CNNs) for 7
image processing, Generative Adversarial Networks (GANs) for image generation, Variational
Autoencoders (VAEs) for image compression and generation, Case studies: Image generation,
Image-to-image translation, etc.
4 Generative Models for Natural Language Processing: Recurrent Neural Networks (RNNs) 7
for text processing, Transformers for text generation and language modeling, Generative
models for text summarization, chatbots, and language translation
5 Advanced Generative AI Topics: Generative models for multimodal data (images, text, 7
audio, etc.), Generative models for sequential data (time series, videos, etc.), Advanced
techniques: Style transfer, CycleGAN
Total 28
Suggested Books:
1. Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play by David Foster,
O'Reilly Media
2. Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
3. Generative Adversarial Networks by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
4. Natural Language Processing (almost) from Scratch" by Collobert et al.
5. Neural Network Methods for Natural Language Processing" by Yoav Goldberg
Deep Learning for Computer Vision with Python" by Adrian Rosebrock

VII Semester
7CS4-21: Deep Learning Lab
Credit: 1 Max. Marks: 100 ( IA:60, ETE:40 )
Course Objectives:
• To provide hands-on experience with deep learning frameworks and tools
• To understand the applications and limitations of deep learning in various domains
• To develop skills in designing, training, and evaluating deep neural networks
Course Outcomes:
CO-1: Implement and train deep neural networks using popular frameworks like TensorFlow or PyTorch
CO-2: Apply deep learning techniques to real-world problems in computer vision, natural language processing,
and time series analysis
CO-3: Understand working principle of various types of neural networks
CO-4: Understand the working principle of convolution neural networks
S. No. List of Experiments
1 Demonstration and implementation of Shallow architecture using Python, TensorFlow and Keras
i) Google Colaboratory - Cloning GitHub repository, Upload Data, Importing Kaggle's dataset,
Basic File operations
ii) Implementing Perceptron,
iii) Digit Classification: Neural network to classify MNIST dataset
2 Basic implementation of a deep Learning models in PyTorch and Tensor Flow. Tune its performance by
adding additional layers provided by the library.
3 Implement custom operations in PyTorch by using deep learning via gradient descent; recursive chain rule
(backpropagation); bias-variance tradeoff, regularization; output units: linear, softmax; hidden units: tanh,
RELU.
4 Implement a simple CNN starting from filtering, Convolution and pooling operations and arithmetic of
these with Visualization in PyTorch and Tensorflow.
5 ConvNet Architectures: Implement a famous convNet architectures - AlexNet, ZFNet, VGG, C3D,
GoogLeNet, ResNet, MobileNet-v1.
6 Convolution Neural Network application using TensorFlow and Keras, i) Classification of MNIST Dataset
using CNN ii) Face recognition using CNN
7 Image denoising (Fashion dataset) using Auto Encoders Handling Color Image in Neural Network aka
Stacked Auto Encoders (Denoising)
8 Text processing, Language Modeling using RNN
9 Time Series Prediction using RNN
10 Sentiment Analysis using LSTM
11 Image generation using GAN
Suggested Books:
1. Deep Learning, Ian Goodfellow Yoshua Bengio Aaron Courville, MIT Press, 2017 (link
https://www.deeplearningbook.org/)
2. Deep Learning Step by Step with Python, N D Lewis, 2016
3. Deep Learning: A Practitioner's Approach, Josh Patterson, Adam Gibson, O'Reilly Media, 2017
4. Deep Learning, Ian Goodfellow Yoshua Bengio Aaron Courville, MIT Press, 2017

5. James Allen “Natural Language Understanding”, Pearson Publication 8th Edition. 2012.
6. François Chollet “Deep Learning with Python,” First Edition, Manning Publication,2018
Neural Networks and Deep Learning, Michael Nielsen, Determination Press (2015) (link:
http://neuralnetworksanddeeplearning.com/ )

VII Semester
7CS7-50 : B.Tech. Project – I (BTP – P1)
0L+0T+3P Mode of evaluation: Report and presentation
Assessment or Evaluation
The evaluation criteria for B. Tech. Project - I
S. No. Category Internal End Term
Assessment Examinations
Max Marks Max Marks in

in % %
1 Project Motivation, Conceptual Design,
Innovativeness, and utility in actual life application 10% 10%
2 Project Ideation, Project Formulation, and Design 10% 10%
3 Project Prototyping & Finalization, Project Planning
& Timeline (Project Viability for 2 semesters) 10% 10%
4 Technology Used and Method 10% 10%
5 Project Execution, Development, Deployment,
Demonstration and Delivery (Working and
completeness) required to justify current semester
work and presentation 30% 30%
6 Report writing and project documentation
(organization of the report, clarity, use of
figure/diagram, writing skills, presentation of result,
paper publication, patent application, etc.) 20% 20%
7 Professional ethics (teamwork, punctuality, novelty,
etc.) 10% 10%
Total 100% 100%

VIII Semester
8CS7-50 : B.Tech. Project -II
0L+0T+3P Mode of evaluation: Report and presentation
Assessment or Evaluation
The evaluation criteria for B. Tech. Project - II
S. No. Category Internal End Term
Assessment Examinations
Max Marks Max Marks in

in % %
1 Project Motivation, Conceptual Design,
Innovativeness, and utility in actual life application 10% 10%
2 Project Ideation, Project Formulation, and Design 10% 10%
3 Technology Used and Method 10% 10%
4 Project Execution, Development, Deployment,
Demonstration and Delivery (Working and
completeness) required to justify current semester
work and presentation 30% 30%
5 Report writing and project documentation
(organization of the report, clarity, use of
figure/diagram, writing skills, presentation of result,
paper publication, patent application, etc.) 20% 20%
6 Professional ethics (teamwork, punctuality, novelty,
etc.) 10% 10%
7 Paper Published in reputed journals (SCE, SCIE,
Scopus, UGC care or any peer-reviewed journal),
Paper publications (International or National
conferences [IEEE, ACM, Springer, etc]), and
presentations at Hackathon (Institute level or SIH) or
any institute, state or national level project
presentation competitions. 10% 10%
Total 100% 100%



VII

Uploaded by

Copyright:

Available Formats

VII

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

VII

Uploaded by

Copyright:

Available Formats

BIKANER TECHNICAL UNIVERSITY, BIKANER

SCHEME & SYLLABUS OF

[Draft Syllabus Subjected to approval]

Effective for the students admitted in year 2021-22 and onwards

Approved by …….. academic council meeting held on ……….

Teaching & Examination Scheme

L = Lecture, T = Tutorial, P = Practical, IA=Internal Assessment, ETE=End TermExam,Cr=Credits

Approved by …….. academic council meeting held on ……….

Teaching & Examination Scheme

10 UI 8CS7-40 Seminar - - 2 - 60 40 100 2

UI 8CS7-50 B.Tech. Project - II - - 3 - 60 40 100 4

12 CCA 8CS8-00 SODECA / Co-Curricular - - - - - 100 100 2

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

5. “GENESIS : Personal Communication Device”. GENESIS 191A321 Document, 1993.

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

Max Marks Max Marks in

Approved by …….. academic council meeting held on ……….

Max Marks Max Marks in

Approved by …….. academic council meeting held on ……….

Approved by …….. academic council meeting held on ……….

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.