0% found this document useful (0 votes)
24 views7 pages

CSE-AI&ML R-20 Syllabus Overview

The document outlines the syllabus for various courses in the CSE-AI&ML program at JNTUK, including Computer Networks, Deep Learning, Deep Learning with TensorFlow, and Object Oriented Analysis and Design. Each course includes objectives, outcomes, and detailed unit topics covering essential concepts and techniques in networking, deep learning methodologies, and object-oriented design principles. Textbooks and reference materials are also provided for further study.

Uploaded by

ashokbonthala04
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
24 views7 pages

CSE-AI&ML R-20 Syllabus Overview

The document outlines the syllabus for various courses in the CSE-AI&ML program at JNTUK, including Computer Networks, Deep Learning, Deep Learning with TensorFlow, and Object Oriented Analysis and Design. Each course includes objectives, outcomes, and detailed unit topics covering essential concepts and techniques in networking, deep learning methodologies, and object-oriented design principles. Textbooks and reference materials are also provided for further study.

Uploaded by

ashokbonthala04
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

R-20 Syllabus for CSE-AI&ML, JNTUK w. e. f.

2020 21

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY: KAKINADA


KAKINADA 533 003, Andhra Pradesh, India

DEPARTMENT OF CSE - ARTIFICIAL INTELLIGENCE & MACHINE LEARNING

L T P C
III B Tech II Sem
3 0 0 3
COMPUTER NETWORKS

Course Objectives:
To provide insight about networks, topologies, and the key concepts.
To gain comprehensive knowledge about the layered communication architectures (OSI and TCP/IP)
and its functionalities.
To understand the principles, key protocols, design issues, and significance of each layers in ISO and
TCP/IP.
To know the basic concepts of network services and various network applications.

Course Outcomes:
By the end of the course, the student will be able to
Demonstrate different network models for networking links OSI, TCP/IP, B-ISDN, N-BISDN and get
knowledge about various communication techniques, methods and protocol standards.
Discuss different transmission media and different switching networks.
Analyze data link layer services, functions and protocols like HDLC and PPP.
Compare and Classify medium access control protocols like ALOHA, CSMA, CSMA/CD, CSMA/CA,
Polling, Token passing, FDMA, TDMA, CDMA protocols
Determine application layer services and client server protocols working with the client server
paradigms like WWW, HTTP, FTP, e-mail and SNMP etc.

UNIT I:
Introduction: Network Types, LAN, MAN, WAN, Network Topologies Reference models- The OSI
Reference Model- the TCP/IP Reference Model - A Comparison of the OSI and TCP/IP Reference Models,
OSI Vs TCP/IP, Lack of OSI models success, Internet History.
Physical Layer Introduction to Guided Media- Twisted-pair cable, Coaxial cable and Fiber optic cable and
unguided media: Wireless-Radio waves, microwaves, infrared.

UNIT II:
Data link layer: Design issues, Framing: fixed size framing, variable size framing, flow control, error

services provided to Network Layer, Elementary Data Link Layer protocols: simplex protocol, Simplex
stop and wait, Simplex protocol for Noisy Channel.
Sliding window protocol: One bit, Go back N, Selective repeat-Stop and wait protocol, Data link layer in
HDLC: configuration and transfer modes, frames, control field, point to point protocol (PPP): framing
transition phase, multiplexing, multi link PPP.

UNIT III:
Media Access Control: Random Access: ALOHA, Carrier sense multiple access (CSMA), CSMA with
Collision Detection, CSMA with Collision Avoidance, Controlled Access: Reservation, Polling, Token
Passing, Channelization: frequency division multiple Access (FDMA), time division multiple
access(TDMA), code division multiple access(CDMA).
Wired LANs: Ethernet, Ethernet Protocol, Standard Ethernet, Fast Ethernet(100 Mbps), Gigabit Ethernet,
10 Gigabit Ethernet.
R-20 Syllabus for CSE-AI&ML, JNTUK w. e. f. 2020 21

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY: KAKINADA


KAKINADA 533 003, Andhra Pradesh, India

DEPARTMENT OF CSE - ARTIFICIAL INTELLIGENCE & MACHINE LEARNING

UNIT IV:
The Network Layer Design Issues Store and Forward Packet Switching-Services Provided to the
Transport layer- Implementation of Connectionless Service-Implementation of Connection Oriented
Service- Comparison of Virtual Circuit and Datagram Networks, Routing Algorithms-The Optimality
principle-Shortest path, Flooding, Distance vector, Link state, Hierarchical, Congestion Control algorithms-
General principles of congestion control, Congestion prevention polices, Approaches to Congestion Control-
Traffic Aware Routing- Admission Control-Traffic Throttling-Load Shedding. Traffic Control Algorithm-
Leaky bucket & Token bucket.
Internet Working: How networks differ, How networks can be connected, Tunnelling, internetwork
routing, Fragmentation, network layer in the internet, IP protocols, IP Version 4 protocol, IPV4 Header
Format, IP addresses, Class full Addressing, CIDR, NAT, Subnets, IP Version 6, The main IPV6 header,
Transition from IPV4 to IPV6, Comparision of IPV4 & IPV6, Internet control protocols- ICMP, ARP,
DHCP

UNIT V:
The Transport Layer: Transport layer protocols: Introduction, services, port number, User datagram
protocol, User datagram, UDP services, UDP applications, Transmission control protocol: TCP services,
TCP features, Segment, A TCP connection, windows in TCP, flow control, Error control, Congestion
control in TCP.
Application Layer: World Wide Web: HTTP, Electronic mail-Architecture, web based mail, email
security, TELENET, local versus remote Logging, Domain Name System: Name Space, DNS in Internet,
Resolution, Caching, Resource Records, DNS messages, Registrars, security of DNS Name Servers, SNMP.

Text Books:
1. Computer Networks, Andrew S Tanenbaum, Fifth Edition. Pearson Education/PHI
2. Data Communications and Networks, Behrouz A. Forouzan, Fifth Edition TMH.

References Books:
1. Data Communications and Networks- Achut S Godbole, AtulKahate
2. Computer Networks, Mayank Dave, CENGAGE
R-20 Syllabus for CSE-AI&ML, JNTUK w. e. f. 2020 21

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY: KAKINADA


KAKINADA 533 003, Andhra Pradesh, India

DEPARTMENT OF CSE - ARTIFICIAL INTELLIGENCE & MACHINE LEARNING

L T P C
III B Tech II Sem
3 0 0 3
DEEP LEARNING

Course Objectives: At the end of the course, the students will be expected to:
Learn deep learning methods for working with sequential data,
Learn deep recurrent and memory networks,
Learn deep Turing machines,
Apply such deep learning mechanisms to various learning problems.
Know the open issues in deep learning, and have a grasp of the current research directions.

Course Outcomes: After the completion of the course, student will be able to
Demonstrate the fundamental concepts learning techniques of Artificial Intelligence, Machine
Learning and Deep Learning.
Discuss the Neural Network training, various random models.
Explain the Techniques of Keras, TensorFlow, Theano and CNTK
Classify the Concepts of CNN and RNN
Implement Interactive Applications of Deep Learning.

UNIT I:
Fundamentals of Deep Learning: Artificial Intelligence, History of Machine learning: Probabilistic
Modeling, Early Neural Networks, Kernel Methods, Decision Trees, Random forests and Gradient Boosting
Machines, Fundamentals of Machine Learning: Four Branches of Machine Learning, Evaluating Machine
learning Models, Overfitting and Underfitting. [Text Book 2]

UNIT II: Introducing Deep Learning: Biological and Machine Vision, Human and Machine Language,
Artificial Neural Networks, Training Deep Networks, Improving Deep Networks. [Text Book3]

UNIT III: Neural Networks: Anatomy of Neural Network, Introduction to Keras: Keras, TensorFlow,
Theano and CNTK, Setting up Deep Learning Workstation, Classifying Movie Reviews: Binary
Classification, Classifying newswires: Multiclass Classification. [Text Book 2]

UNIT IV:
Convolutional Neural Networks: Nerual Network and Representation Learing, Convolutional Layers,
Multichannel Convolution Operation, Recurrent Neural Networks: Introduction to RNN, RNN Code,
PyTorch Tensors: Deep Learning with PyTorch, CNN in PyTorch. [Text Book 3]

UNIT V:
Interactive Applications of Deep Learning: Machine Vision, Natural Language processing, Generative
Adversial Networks, Deep Reinforcement Learning. [Text Book 1]
Deep Learning Research: Autoencoders, Deep Generative Models: Boltzmann Machines Restricted
Boltzmann Machines, Deep Belief Networks. [Text Book 1]
R-20 Syllabus for CSE-AI&ML, JNTUK w. e. f. 2020 21

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY: KAKINADA


KAKINADA 533 003, Andhra Pradesh, India

DEPARTMENT OF CSE - ARTIFICIAL INTELLIGENCE & MACHINE LEARNING

Text Books:
1. Deep Learning- Ian Goodfellow, Yoshua Bengio and Aaron Courvile, MIT Press, 2016
2. Deep Learning with Python - Francois Chollet, Released December 2017, Publisher(s): Manning
Publications, ISBN: 9781617294433
3. Deep Learning Illustrated: A Visual, Interactive Guide to Artificial Intelligence - Jon Krohn, Grant
Beyleveld, Aglaé Bassens, Released September 2019, Publisher(s): Addison-Wesley Professional,
ISBN: 9780135116821
4. Deep Learning from Scratch - Seth Weidman, Released September 2019, Publisher(s): O'Reilly
Media, Inc., ISBN: 9781492041412

Reference Books:
1. Artificial Neural Networks, Yegnanarayana, B., PHI Learning Pvt. Ltd, 2009.
2. Matrix Computations, Golub, G.,H., and Van Loan,C.,F, JHU Press,2013.
3. Neural Networks: A Classroom Approach, Satish Kumar, Tata McGraw-Hill Education, 2004.

Web Link:
Swayam NPTEL: Deep Learning: [Link]
R-20 Syllabus for CSE-AI&ML, JNTUK w. e. f. 2020 21

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY: KAKINADA


KAKINADA 533 003, Andhra Pradesh, India

DEPARTMENT OF CSE - ARTIFICIAL INTELLIGENCE & MACHINE LEARNING

L T P C
III B Tech II Sem
0 0 3 1.5
DEEP LEARNING WITH TENSORFLOW

Course Outcomes:
On completion of this course, the student will be able to
Implement deep neural networks to solve real world problems
Choose appropriate pre-trained model to solve real time problem
Interpret the results of two different deep learning models

Software Packages required:


Keras
Tensorflow
PyTorch

List of Experiments:
1. Implement multilayer perceptron algorithm for MNIST Hand written Digit Classification.
2. Design a neural network for classifying movie reviews (Binary Classification) using IMDB dataset.
3. Design a neural Network for classifying news wires (Multi class classification) using Reuters
dataset.
4. Design a neural network for predicting house prices using Boston Housing Price dataset.
5. Build a Convolution Neural Network for MNIST Hand written Digit Classification.
6. Build a Convolution Neural Network for simple image (dogs and Cats) Classification
7. Use a pre-trained convolution neural network (VGG16) for image classification.
8. Implement one hot encoding of words or characters.
9. Implement word embeddings for IMDB dataset.
10. Implement a Recurrent Neural Network for IMDB movie review classification problem.

Text Books:
1.

References:
1. [Link]
R-20 Syllabus for CSE-AI&ML, JNTUK w. e. f. 2020 21

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY: KAKINADA


KAKINADA 533 003, Andhra Pradesh, India

DEPARTMENT OF CSE - ARTIFICIAL INTELLIGENCE & MACHINE LEARNING

L T P C
IV B Tech I Sem
3 0 0 3
OBJECT ORIENTED ANALYSIS AND DESIGN
(Professional Elective-V)

Course Objectives: The main objective is the students to


Become familiar with all phases of OOAD.
Master the main features of the UML.
Master the main concepts of Object Technologies and how to apply them at work and develop the
ability to analyze and solve challenging problem in various domains.
Learn the Object design Principles and understand how to apply them towards Implementation.

Course Outcomes: After finishing this course student will be able to:
Analyze the nature of complex system and its solutions.
Illustrate & relate the conceptual model of the UML, identify & design the classes and relationships
Analyze &Design Class and Object Diagrams that represent Static Aspects of a Software System and
apply basic and Advanced Structural Modeling Concepts for designing real time applications.
Analyze & Design behavioral aspects of a Software System using Use Case, Interaction and Activity
Diagrams.
Analyze & Apply techniques of State Chart Diagrams and Implementation Diagrams to model
behavioral aspects and Runtime environment of Software Systems.

UNIT I:
Introduction: The Structure of Complex systems, The Inherent Complexity of Software, Attributes of
Complex System, Organized and Disorganized Complexity, Bringing Order to Chaos, Designing Complex
Systems. Case Study: System Architecture: Satellite-Based Navigation

UNIT II:
Introduction to UML: Importance of modeling, principles of modeling, object oriented modeling,
conceptual model of the UML, Architecture, and Software Development Life Cycle. Basic Structural
Modeling: Classes, Relationships, common Mechanisms, and diagrams. Case Study: Control System:
Traffic Management.

UNIT III:
Class & Object Diagrams: Terms, concepts, modeling techniques for Class & Object Diagrams.
Advanced Structural Modeling: Advanced classes, advanced relationships, Interfaces, Types and Roles,
Packages. Case Study: AI: Cryptanalysis.

UNIT IV:
Basic Behavioral Modeling-I: Interactions, Interaction diagrams Use cases, Use case Diagrams, Activity
Diagrams. Case Study: Web Application: Vacation Tracking System

UNIT V:
Advanced Behavioral Modeling: Events and signals, state machines, processes and Threads, time and
space, state chart diagrams. Architectural Modeling: Component, Deployment, Component diagrams and
Deployment diagrams
Case Study: Weather Forecasting
R-20 Syllabus for CSE-AI&ML, JNTUK w. e. f. 2020 21

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY: KAKINADA


KAKINADA 533 003, Andhra Pradesh, India

DEPARTMENT OF CSE - ARTIFICIAL INTELLIGENCE & MACHINE LEARNING

Text Books:
1. Grady BOOCH, Robert A. Maksimchuk, Michael W. ENGLE, Bobbi J. Young, Jim Conallen, Kellia
-
2. Grady Booch, James Rumbaugh, Ivar Jacobson: The Unified Modeling Language User Guide,
Pearson Education.

Reference Books:
1. Meilir Page-Jones: Fundamentals of Object Oriented Design in UML, Pearson Education.
2. Pascal Roques: Modeling Software Systems Using UML2, WILEY- Dreamtech India Pvt. Ltd.
3. Atul Kahate: Object Oriented Analysis & Design, The McGraw-Hill Companies.
4. Appling UML and Patterns: An introduction to Object Oriented Analysis and Design and Unified
Process, Craig Larman, Pearson Education.

Common questions

Powered by AI

The OSI model consists of seven layers each with specific functions, including physical (layer 1), data link (layer 2), network (layer 3), transport (layer 4), session (layer 5), presentation (layer 6), and application (layer 7) layers . Conversely, the TCP/IP model has four layers: network interface, internet, transport, and application. The OSI model is more theoretical, emphasizing protocol design and development, whereas the TCP/IP model is more practical, built specifically for the internet and emphasizing real-world implementation .

Deep reinforcement learning applies neural networks to decision-making, enabling autonomous agents to exploit complex, high-dimensional environments. Such applications are transformative in strategic fields like robotics, where machines learn optimal actions through trial and error, embodying efficiency and adaptability to changing scenarios. It poses challenges in computational cost, convergence guarantees, and scalability, necessitating robust frameworks for implementation .

IPv4 uses a 32-bit address scheme allowing 4.3 billion addresses, whereas IPv6 uses a 128-bit scheme offering a vastly larger address space . The IPv4 header includes fields such as version, header length, and total length, whereas the IPv6 header is simplified with fixed length and necessary fields like flow label for quality of service .

Overfitting occurs when a neural network learns the training data excessively well, capturing noise instead of general patterns. This results in poor performance on unseen data. It is a significant challenge in training neural networks, necessitating techniques like regularization, dropout, and cross-validation to maintain a balance between memorization and generalization .

Object diagrams in UML represent instances of classes and are instrumental in analyzing real-time dynamic behavior between objects. While class diagrams display static structure, object diagrams showcase the practical usage and interaction of objects over time, providing insights into realistic scenarios and helping identify issues not visible in static analysis alone .

The leaky bucket algorithm controls traffic by sending data at a steady rate irrespective of burstiness, collecting packets and releasing them at a constant rate . The token bucket algorithm provides more flexibility, allowing bursts of traffic by accumulating tokens at a steady rate; packets can be sent as long as there are enough tokens, complementing the network's capability to handle bursts .

State chart diagrams are used to model the dynamic behavior of an individual object throughout its lifecycle by representing states, transitions, events, and actions . They help to visualize how objects react to external stimuli and change state, providing clarity on the object's behavior in different scenarios and enhancing understanding of system design .

The sliding window protocol is crucial in managing the flow of frames between sender and receiver, maintaining data integrity and efficiency . It allows multiple frames to be sent by not requiring an acknowledgment for every single frame, thus optimizing bandwidth usage. The protocols like Go-Back-N and Selective Repeat in sliding window adjust retransmissions based on frame acknowledgment, enhancing reliability .

IP addresses are traditionally divided into five classes: A, B, C, D, and E. Class A addresses are designed for large networks, with the first octet as a network part. Class B is for medium networks with the first two octets defining the network. Class C supports smaller networks using the first three octets. Class D is used for multicast groups, and Class E is reserved for future or experimental purposes .

Convolutional Neural Networks are pivotal in computer vision due to their ability to automatically and adaptively learn spatial hierarchies of features. By applying different convolutional kernels, CNNs can detect edges, textures, and patterns essential for tasks like object recognition, object detection, and image segmentation . They are highly effective in reducing dimensionality while preserving essential features, thanks to pooling layers .

You might also like