BE Syllabus 2022-23
BE Syllabus 2022-23
Curriculum
for
Fourth Year of Computer Engineering
(2019 Course)
(With effect from 2022-23)
www.unipune.ac.in
Faculty of Engineering Savitribai Phule Pune University
Mid-Sem
End-Sem
Practical
Practical
Practical
Oral/Pre
Tutorial
Tutorial
Lecture
Lecture
Term
Total
Total
work
410250 High Performance
03 - - 30 70 - - - 100 03 03
Computing
410251 Deep Learning 03 - - 30 70 - - - 100 03 03
410252 Elective V 03 - - 30 70 - - - 100 03 03
410253 Elective VI 03 - - 30 70 - - - 100 03 03
410254 Laboratory Practice V - 02 - - - 50 50 - 100 01 01
410255 Laboratory Practice VI - 02 - - - 50 - - 50 01 01
410256 Project Stage II - 06 - - - 100 - 50 150 06 06
Total Credit 12 08 - 20
Total 12 10 - 120 280 200 50 50 700 12 08 - 20
410257 Audit Course 8 Grade
Elective V Elective VI
410252(A) Natural Language Processing 410253(A) Pattern Recognition
410252(B) Image Processing 410253(B) Soft Computing
410252(C) Software Defined Networks 410253(C) Business Intelligence
410252(D) Advanced Digital Signal Processing 410253(D) Quantum Computing
410252(E) Open Elective 410253(E) Open Elective
Lab Practice V: Lab Practice VI:
Laboratory assignments Courses- 410250, 410251 Laboratory assignments Courses- 410252, 410253
Audit Course 8(AC8) Options:
AC8- I Usability Engineering
AC8- II Conversational Interfaces
AC8- II Social Media and Analytics
AC8- IV MOOC- Learn New Skills
AC8- V Emotional Intelligence
SEMESTER
VIII
Home
Savitribai Phule Pune University
Fourth Year of Computer Engineering (2019 Course) Home
Course Contents
Unit I Introduction to Parallel Computing 09 Hours
Introduction to Parallel Computing: Motivating Parallelism, Modern Processor: Stored-
program computer architecture, General-purpose Cache-based Microprocessor architecture. Parallel
Programming Platforms: Implicit Parallelism, Dichotomy of Parallel Computing Platforms,
Physical Organization of Parallel Platforms, Communication Costs in Parallel Machines. Levels of
parallelism, Models: SIMD, MIMD, SIMT, SPMD, Data Flow Models, Demand-driven
Computation, Architectures: N-wide superscalar architectures, multi-core, multi-threaded.
#Exemplar/Case
Studies Case study: Multi-core System
*Mapping of Course
Outcomes for Unit I CO1
Unit II Parallel Algorithm Design 09 Hours
Global System for Mobile Communications (GSM) architecture , Mobile Station, Base Station
System, Switching subsystem, Security, Data Services, HSCSD, GPRS - GPRS system and
protocol architecture 2.3 UTRAN, UMTS core network; Improvements on Core Network, 802.11
Architecture 802.11a, 802.11b standard
#Exemplar/Case IPoC: A New Core Networking Protocol for 5G Networks.
Studies
Syllabus for Fourth Year of Computer Engineering ` #72/128
Faculty of Engineering Savitribai Phule Pune University
*Mapping of Course CO2
Outcomes for Unit II
Unit III Parallel Communication 09 Hours
Basic Communication: One-to-All Broadcast, All-to-One Reduction, All-to-All Broadcast and
Reduction, All-Reduce and Prefix-Sum Operations, Collective Communication using MPI: Scatter,
Gather, Broadcast, Blocking and non blocking MPI, All-to-All Personalized Communication,
Circular Shift, Improving the speed of some communication operations.
#Exemplar/Case Case study: Monte-Carlo Pi computing using MPI
Studies
*Mapping of Course CO3
Outcomes for UnitIII
Sources of Overhead in Parallel Programs, Performance Measures and Analysis: Amdahl's and
Gustafson's Laws, Speedup Factor and Efficiency, Cost and Utilization, Execution Rate and
Redundancy, The Effect of Granularity on Performance, Scalability of Parallel Systems, Minimum
Execution Time and Minimum Cost, Optimal Execution Time, Asymptotic Analysis of Parallel
Programs. Matrix Computation: Matrix-Vector Multiplication, Matrix-Matrix
Multiplication.
Scope of Parallel Computing, Parallel Search Algorithms: Depth First Search(DFS), Breadth First
Search( BFS), Parallel Sorting: Bubble and Merge, Distributed Computing: Document
classification, Frameworks – Kuberbets, GPU Applications, Parallel Computing for AI/ ML
#Exemplar/Case Case study: Disaster detection and management/ Smart Mobility/Urban
Studies planning
*Mapping of Course CO6
Outcomes for Unit
VI
Learning Resources
Home
Savitribai Phule Pune University
Fourth Year of Computer Engineering (2019 Course)
410251: Deep Learning
Teaching Scheme: Examination Scheme:
Credit
In-Sem (Paper): 30 Marks
TH: 03 Hours/Week 03
End-Sem (Paper): 70 Marks
Prerequisite Courses: Machine Learning (410242)
Companion Course: Laboratory Practice V(410254)
Course Objectives:
● To understand the basics of neural networks.
● Comparing different deep learning models.
● To understand the Recurrent and Recursive nets in Deep Learning
● To understand the basics of deep reinforcement Learning models.
● To analyze Types of Networks.
● To Describe Reinforcement Learning.
Course Outcomes:
On completion of the course, student will be able to–
CO1: Understand the basics of Deep Learning and apply the tools to implement deep
learningapplications
CO2: Evaluate the performance of deep learning models (e.g., with respect to the bias-variance trade-
off, overfitting and underfitting, estimation of test error).
CO3: To apply the technique of Convolution (CNN) and Recurrent Neural Network (RNN)
for implementing Deep Learning models
CO4: To implement and apply deep generative models.
CO5: Construct and apply on-policy reinforcement learning algorithms
CO6:To Understand Reinforcement Learning Process
Course Contents
Unit I Foundations of Deep learning 07 Hours
What is machine learning and deep learning?,Supervised and Unsupervised Learning, bias variance
tradeoff, hyper parameters, under/over fitting regularization, Limitations of machine learning, History of
deep learning, Advantage and challenges of deep learning. Learning representations from data ,
Understanding how deep learning works in three figures, Common Architectural Principles of Deep
Network, Architecture Design, Applications of Deep learning, Introduction and use of popular industry
tools such as TensorFLow,
Keras, PyTorch, Caffe, Shogun.
Home
Savitribai Phule Pune University
Fourth Year of Computer Engineering (2019 Course)
Elective V
410252(C): Software Defined Networks
Teaching Scheme: Credit: Examination Scheme:
TH: 3 3 Mid-Semester (TH) : 30
Hours/Week End-Sem (TH): 70
Prerequisites Courses: Computer Networks and Security(310244)
Companion Course: Laboratory Practice VI(410255)
Course Objectives:
To learn the fundamentals of software defined networks and understand
Differentiation between traditional networks and software defined networks
To gain conceptual understanding of Software Defined Networking (SDN) and its role in
Data Center.
To study about the SDN Programming.
To study industrial deployment use-cases of SDN.
To study about the various applications of SDN
To Describe SDN Framework.
Course Outcomes:
On completion of the course, student will be able to–
CO1: Interpret the need of Software Defined networking solutions.
CO2: Analyze different methodologies for sustainable Software Defined Networkingsolutions.
CO3: Select best practices for design, deploy and troubleshoot of next generation networks.
CO4: Develop programmability of network elements.
CO5: Demonstrate virtualization and SDN Controllers using Open Flow protocol
CO6: Design and develop various applications of SDN
Course Contents
Unit I Introduction 07 Hours
Challenges of traditional networks, History of Software Defined Networking (SDN), Modern Data
Center – Traditional Switch Architecture – Why SDN – Evolution of SDN – How SDN Works –
Centralized and Distributed Control and Date Planes.
#Exemplar/Case Video Streaming
Studies https://kempsdn.com/what-is-sdn-and-use-cases/video-streaming/
*Mapping of Course CO1,CO2
Outcomes for Unit I
Unit II OPEN FLOW & SDN CONTROLLERS 07 Hours
Open Flow Overview, The Open Flow Switch, The Open Flow Controller, Open Flow Ports,
Message Types, Pipeline Processing, Flow Tables, Matching, Instructions, Action Set and List,
Open Flow Protocol, Proactive and Reactive Flow, Timers, Open Flow Limitations, Open Flow
Advantages and Disadvantages, Open v Switch Features, Drawbacks of Open SDN, Introduction to
SDN controller.
Home
Savitribai Phule Pune University
Fourth Year of Computer Engineering (2019 Course)
410253A: Elective-VI Business Intelligence
Teaching Scheme: Credit: Examination Scheme:
TH: 03 03 Mid-Semester (TH) : 30 Marks
Hours/Week End-Sem (TH): 70 Marks
Prerequisites Courses: 310241: Database Management System,310251:Data Science & Big data
Analytics,410242: Machine Learning
Companion Course: 410256:Laboratory Practice VI
● Course Objectives:
1. To introduce the concepts and components of Business Intelligence (BI)
2. To evaluate the technologies that make up BI (data warehousing, OLAP)
3. To identify the technological architecture of BI systems·
4. To explain different data preprocessing techniques
5. To identify machine learning model as per business need
6. To understand the BI applications in marketing, logistics, finance and telecommunication sector
● Course Outcomes: On completion of this course, the students will be able to
CO1: Differentiate the concepts of Decision Support System & Business Intelligence
CO2:Use Data Warehouse & Business Architecture to design a BI system.
CO3:Build graphical reports
CO4:Apply different data preprocessing techniques on dataset
CO5:mplement machine learning algorithms as per business needs
CO6:Identify role of BI in marketing, logistics, and finance and telecommunication sector
Course Contents
Unit I Introduction to Decision support systems and 07 Hours
Business intelligence
Decision support systems: Definition of system, representation of the decision-making process, evolution of
information systems, Decision Support System, Development of a decision support system, the four stages of
Simon’s decision-making process, and common strategies and approaches of decision makers
Business Intelligence: BI, its components & architecture, previewing the future of BI, crafting a better
experience for all business users, End user assumptions, setting up data for BI, data, information and
knowledge, The role of mathematical models, Business intelligence architectures, Ethics and business
intelligence
#Exemplar/Case Decision support system in business intelligence:
Studies https://www.riverlogic.com/blog/five-decision-support-system-examples
*Mapping of Course CO1
Outcomes for Unit I
Unit II The Architecture of DW and BI 07 Hours
BI and DW architectures and its types - Relation between BI and DW - OLAP (Online analytical processing)
definitions - Different OLAP Architectures-Data Models-Tools in Business Intelligence-Role of DSS, EIS,
MIS and digital Dash boards – Need for Business Intelligence
Difference between OLAP and OLTP - Dimensional analysis - What are cubes? Drill-down and roll-up -
slice and dice or rotation - OLAP models - ROLAP versus MOLAP - defining schemas: Stars, snowflakes
and fact constellations.
#Exemplar/Case Power BI Case Study – How the tool reduced hassles of Heathrow &
Studies Edsby:
https://data-flair.training/blogs/power-bi-case-study/
*Mapping of Course CO3
Outcomes for Unit
III
Unit IV Data preparation 07 Hours
Data validation: Incomplete data , Data affected by noise .Data transformation: Standardization , Feature
extraction. Data reduction : Sampling, Feature selection, Principal component analysis, Data discretization
.Data exploration : 1.Univarate analysis :Graphical analysis of categorical attributes ,Graphical analysis of
numerical attributes , Measures of central tendency for numerical attributes , Measures of dispersion for
numerical attributes, Identification of outliers for numerical attributes 2.Bivariate analysis: Graphical
analysis , Measures of correlation for numerical attributes , Contingency tables for categorical attributes,
3.Multivariate analysis: Graphical analysis , Measures of correlation for numerical attributes
#Exemplar/Case Case study on Data preparation phase of BI system
Studies https://blog.panoply.io/load-and-transform-how-to-prepare-your-data-for-business-
intelligence
*Mapping of Course CO4
Outcomes for Unit
IV
e-Books :
1. https://www.knime.com/sites/default/files/inline-images/KNIME_quickstart.pdf
2.www.cs.ccsu.edu/~markov/weka-tutorial.pdf
3.http://www.biomedicahelp.altervista.org/Magistrale/Clinics/BIC_PrimoAnno/IdentificazioneModelliDataMining/Bus
iness%20Intelligence%20-%20Carlo%20Vercellis.pdf
4. https://download.e-bookshelf.de/download/0000/5791/06/L-G-0000579106-0002359656.pdf
Course Outcomes:
CO1: Analyze and measure performance of sequential and parallel algorithms.
CO2: Design and Implement solutions for multicore/Distributed/parallel environment.
CO3: Identify and apply the suitable algorithms to solve AI/ML problems.
CO4: Apply the technique of Deep Neural network for implementing Linear
regression and classification.
CO5: Apply the technique of Convolution (CNN) for implementing Deep Learning models.
CO6: Design and develop Recurrent Neural Network (RNN) for prediction.
Guidelines for Instructor's Manual
Laboratory Practice V is for practical hands on for core courses High Performance Computing and
Data Learning. The instructor’s manual is to be developed as a hands-on resource and as ready
reference. The instructor's manual need to include prologue (about University/program/ institute/
department/foreword/ preface etc), University syllabus, conduction and Assessment guidelines,
topics under consideration-concept, objectives, outcomes, set of typical applications/assignments/
guidelines, references among others.
Continuous assessment of laboratory work is to be done based on overall performance and lab
assignments performance of student. Each lab assignment assessment will assign grade/marks based
on parameters with appropriate weightage. Suggested parameters for overall assessment as well as
each lab assignment assessment include- timely completion, performance, innovation, efficient codes,
punctuality and neatness reserving weightage for successful mini-project completion and related
documentation.
● Both internal and external examiners should jointly frame suitable problem statements for
practical examination based on the term work completed.
● During practical assessment, the expert evaluator should give the maximum weightage to the
satisfactory implementation of the problem statement.
● The supplementary and relevant questions may be asked at the time of evaluation to test the
student‟s for advanced learning, understanding of the fundamentals, effective and efficient
implementation.
● Encouraging efforts, transparent evaluation and fair approach of the evaluator will not create
any uncertainty or doubt in the minds of the students. So adhering to these principles will
consummate our team efforts to the promising boost to the student's academics.
Group 1
1. Design and implement Parallel Breadth First Search and Depth First Search based on existing
algorithms using OpenMP. Use a Tree or an undirected graph for BFS and DFS .
2. Write a program to implement Parallel Bubble Sort and Merge sort using OpenMP. Use
existing algorithms and measure the performance of sequential and parallel algorithms.
3. Implement Min, Max, Sum and Average operations using Parallel Reduction.
4. Write a CUDA Program for :
1. Addition of two large vectors
2. Matrix Multiplication using CUDA C
5. Implement HPC application for AI/ML domain.
Group 2
6. Mini Project: Evaluate performance enhancement of parallel Quicksort Algorithm using MPI
9. Mini Project: Implement Non-Serial Polyadic Dynamic Programming with GPU Parallelization
Group 1
1. Linear regression by using Deep Neural network: Implement Boston housing price prediction
problem by Linear regression using Deep Neural network. Use Boston House price prediction
dataset.
2. Classification using Deep neural network (Any One from the following)
1. Multiclass classification using Deep Neural Networks: Example: Use the OCR letter
recognition dataset https://archive.ics.uci.edu/ml/datasets/letter+recognition
2. Binary classification using Deep Neural Networks Example: Classify movie reviews into
positive" reviews and "negative" reviews, just based on the text content of the reviews.
Use IMDB dataset
3. Convolutional neural network (CNN) (Any One from the following)
Use any dataset of plant disease and design a plant disease detection system using CNN.
Use MNIST Fashion Dataset and create a classifier to classify fashion clothing into
categories.
4. Recurrent neural network (RNN) Use the Google stock prices dataset and design a time series
analysis and prediction system using RNN.
Group 2
5. Mini Project: Human Face Recognition
6. Mini Project: Gender and Age Detection: predict if a person is a male or female and also their age
7. Mini Project: Colorizing Old B&W Images: color old black and white images to colorful images
CO1 1 - 1 1 - 2 1 - - - - -
CO2 1 2 1 - - 1 - - - - - 1
CO3 - 1 1 1 1 1 - - - - - -
CO4 3 3 3 - 3 - - - - - - -
CO5 3 3 3 3 3 - - - - - - -
CO6 3 3 3 3 3 - - - - - - -
CO7 3 3 3 3 3 - - - - - -