Information Technology • 7th SemesterCore / Standard CurriculumChange Track

Information Technology — 7th Semester Syllabus

CSE (Internet of Things)

Credits Allocation Table (L-T-P Structure)

Course TitleCodeLTPCredits
Biology for Engineers1007083003
Deep Learning1557013003
Program Elective-IV1557XX3003
Open Elective-I1007XX3003
Deep Learning Lab155701P0021
Summer Entrepreneurship – III1007070008
Project-I100709P0006
TOTAL----27

Biology for Engineers

100708
Theory Course • 6 Units
View PYQ Papers

Unit 1.0: Introduction Biology for Engineers

  • Purpose: To convey that Biology is as important a scientific discipline as Mathematics, Physics and Chemistry
  • Bring out the fundamental differences between science and engineering by drawing a comparison between eye and camera, Bird flying and aircraft
  • Mention the most exciting aspect of biology as an independent scientific discipline
  • Why we need to study biology?
  • Discuss how biological observations of 18th Century that lead to major discoveries
  • Examples from Brownian motion and the origin of thermodynamics by referring to the original observation of Robert Brown and Julius Mayor
  • These examples highlight the fundamental importance of observations in any scientific inquiry

Unit 2.0: Classification

  • Purpose: To convey that classification per se is not what biology is all about. The underlying criterion, such as morphological, biochemical or ecological be highlighted
  • Hierarchy of life forms at phenomenological level
  • A common thread weaves this hierarchy Classification
  • Discuss classification based on (a) cellularity- Unicellular or multicellular (b) ultrastructure- prokaryotes or eucaryotes (c) energy and Carbon utilization - Autotrophs, heterotrophs, lithotopes (d) Ammonia excretion - aminotelic, urocotelic, ureotelic (e) Habitat- acquatic or terrestrial (f) Molecular taxonomy- three major kingdoms of life
  • A given organism can come under different category based on classification
  • Model organisms for the study of biology come from different groups. E.coli, S.cerevisiae, D. Melanogaster, C. elegance, A. Thaliana, M. musculus

Unit 3.0: Genetics and Biomolecules

  • Genetics: Purpose: To convey that "Genetics is to biology what Newton's laws are to Physical Sciences"
  • Mendel's Concept of segregation and independent Gene mapping, Gene interaction, Epistasis
  • Meiosis and Mitosis be taught as a part of genetics. Emphasis to be give not to the mechanics of cell division nor the phases but how genetic material passes from parent to offspring
  • Concepts of recessiveness and dominance
  • Concept of mapping of phenotype to genes
  • Discuss about the single gene disorders in humans
  • Discuss the concept of complementation using human genetics
  • Biomolecules: Purpose: To convey that all forms of life has the same building blocks and yet the manifestations are as diverse as one can imagine
  • Molecules of life. In this context discuss monomeric units and polymeric structures
  • Discuss about sugars, starch and cellulose. Amino acids and proteins. Nucleotides and DNA/RNA. Two carbon units and lipids

Unit 4.0: Enzymes and Information Transfer

  • Enzymes: Purpose: To convey that without catalysis life would not have existed on earth
  • Enzymology: How to monitor enzyme catalysed reactions
  • How does an enzyme catalyse reactions? Enzyme classification. Mechanism of enzyme action. Discuss at least two examples. Enzyme kinetics and kinetic parameters. Why should we know these parameters to understand biology? RNA catalysis
  • Information Transfer: Purpose: The molecular basis of coding and decoding genetic information is universal
  • Molecular basis of information transfer. DNA as a genetic material. Hierarchy of DNA structure- from single stranded to double helix to nucleosomes. Concept of genetic code. Universality and degeneracy of genetic code. Define gene in terms of complementation and recombination

Unit 5.0: Macromolecular Analysis and Metabolism

  • Macromolecular Analysis: Purpose: To analyse biological processes at the reductionistic level. Proteins- structure and function. Hierarch in protein structure. Primary secondary, tertiary and quaternary structure. Proteins as enzymes, transporters, receptors and structural elements
  • Metabolism: Purpose: The fundamental principles of energy transactions are the same in physical and biological world. Thermodynamics as applied to biological systems. Exothermic and endothermic versus endergonic and exergonic reactions. Concept of Keq and its relation to standard free energy. Spontaneity. ATP as an energy currency. This should include the breakdown of glucose to CO2 + H2O (Glycolysis and Krebs cycle) and synthesis of glucose from CO2 and H2O (Photosynthesis). Energy yielding and energy consuming reactions. Concept of Energy charge

Unit 6.0: Microbiology

  • Concept of single celled organisms. Concept of species and strains. Identification and classification of microorganisms. Microscopy. Ecological aspects of single celled organisms. Sterilization and media compositions. Growth kinetics
  • Plant Physiology covering, Transpiration; Mineral nutrition Ecology covering, Ecosystems- Components, types, flow of matter and energy in an ecosystem; Community ecology- Characteristics, frequency, life forms, and biological spectrum; Ecosystem structure- Biotic and abiotic factors, food chain, food web, ecological pyramids

Deep Learning

155701
Theory Course • 6 Units
View PYQ Papers

Unit 1.0: Introduction

  • Definition of AI, Machine Learning, Deep Learning
  • Human Brain vs Artificial Neuron, Biological neuron and artificial neuron analogy
  • Neuron Models: McCulloch-Pitts neuron, Activation functions (Sigmoid, Tanh, ReLU, Leaky ReLU, Softmax)
  • Perceptron, Multilayer Perceptrons, Back-Propagation Algorithm, XOR Problem
  • Difficulty of training deep neural networks, Discussion on deep learning frameworks

Unit 2.0: Optimization & Hyperparameter Tuning

  • Gradient Descent, stochastic gradient, momentum, RMSProp, ADAM
  • Regularization for Deep Learning: Parameter Norm Penalties - L2 Parameter Regularization, Dataset Augmentation, Semi-Supervised Learning
  • Optimization for Training Deep Models

Unit 3.0: Convolutional Neural Networks (CNN)

  • Convolution operation, Filters, Padding, Stride, Pooling, Normalization
  • Modern CNN architectures: LeNet, AlexNet, VGG, GoogLeNet, ResNet, Inception, EfficientNet
  • Transfer Learning & Fine-tuning, Image Augmentation

Unit 4.0: Sequence Modeling

  • RNN, Vanishing Gradient in RNN, LSTM & GRU networks, Bidirectional RNNs
  • Applications: Text generation, Sentiment analysis, Time-series forecasting

Unit 5.0: Attention and Transformers

  • Attention mechanism (Self-attention, Multi-head)
  • Positional Autoencoders, Encoder-Decoder architecture, Sparse Autoencoders, Denoising Autoencoders, Variational Autoencoders (VAE)
  • Transformer architecture, BERT, GPT

Unit 6.0: Generative Models

  • Basics, GANs (Generative Adversarial Networks)- Generator & Discriminator, DCGAN, CycleGAN, StyleGAN
  • Applications of GANs

Program Elective-IV

1557XX
Theory Course • Course Details
View PYQ Papers
Available Elective Tracks & Options (5):

Program Elective: Privacy and Security in IoT

155702

Unit 1.0: Security in IoT

IoT security: Vulnerabilities, Attacks and Countermeasures • Security Engineering for IoT development • IoT security lifecycle

Unit 2.0: Network Robustness and Malware Propagation Control in IoT

Network Robustness • Fusion Based Defense Scheme • Sequential Defense Scheme • Location Certificate Based Scheme • Sybil node detection scheme • Formal Modeling and Verification • Sybil Attack Detection in Vehicular Networks • Performance evaluation of various Malware Dynamics Models • Analysis of Attack Vectors on Smart Home Systems

Unit 3.0: Crypto Foundations

Block ciphers, message integrity, authenticated encryption, hash functions, Merkle trees, elliptic curves • Public-key crypto (PKI), signature algorithms

Unit 4.0: Privacy Preservation in IoT

Privacy Preservation Data Dissemination: Network Model, Threat Model - Problem formulation and definition - Baseline data dissemination - Spatial Privacy Graph based data dissemination - Experiment Validation • Smart building concept- Privacy Threats in Smart Building - Privacy Preserving Approaches in Smart Building - Smart Meter Privacy Preserving Approaches

Unit 5.0: Trust Models for IoT

Trust Model Concepts - Public Key Infrastructures Architecture Components - Public Key Certificate Formats - Design Considerations for Digital Certificates - Public Key Reference Infrastructure for the IoT • Authentication in IoT - Computational Security for IoT

Unit 6.0: Security Protocols for IoT Access Networks

Time Based Secure Key Generation - Security Access Algorithm: Unidirectional, Bidirectional Transmission - Cognitive Security - IoT Security Framework - Secure IoT Layers - Secure Communication Links in IoT - Secure Resource Management, Secure IoT Databases

Program Elective: Application of IoT in Robotics

155703

Unit 1.0: Introduction To Robotics and IoT

Introduction of Robotics: Definition, history, and application of robotics • Types of robots: mobile robots, autonomous robots, industrial robots • Introduction to IoT: Definition, components, and architecture • Evolution of IoT & enabling technologies (RFID, WSN, Cloud, Big Data)

Unit 2.0: IoT Sensors and Actuators

Types of IoT Sensors: Temperature, humidity, pressure, proximity • Actuators in IoT: DC motors, servo motors, stepper motors, solenoids • Selection criteria of sensors and actuators into robotic systems • Robotic perception enhancement using IoT sensors • Integration of cameras, LiDAR, ultrasonic sensors with IoT • Real-time control of robotic actuators using IoT data • Interfacing sensors/actuators with microcontrollers (Arduino/RPi/NodeMCU)

Unit 3.0: Design Principles for Connected Devices

IoT/M2M System Layers and Design Standardization • Communication technologies: Wi-Fi, BLE, ZigBee, LoRa, RFID • Data Enrichment, Data Consolidation and Device Management at Gateway • Web communication protocols (HTTP, MQTT, CoAP, WebSockets) • Message Communication Protocols; Internet Connectivity; Internet connectivity and IP addressing in IoT devices

Unit 4.0: IoT Platforms and Middleware

Overview of IoT platforms: AWS IoT, Azure IoT, Google Cloud IoT • Middleware for integrating IoT devices and robotics • Hands-on experience with setting up and using IoT platforms for robotics applications • Introduction to edge computing and its relevance in robotics

Unit 5.0: Data Acquisition and Processing

Data acquisition from IoT sensors and actuators in robotic systems • Data logging formats: JSON, CSV, MQTT payloads • Data processing techniques: Filtering, aggregation, normalization • Real-time data analysis in robotics applications

Unit 6.0: IoT-Enabled Robotic Applications & Case Studies

Robotic Applications: Smart robotic systems using IoT; IoT-based mobile robots; Industrial IoT (IIoT) robotics applications; Healthcare & service robots with IoT; Autonomous delivery robots • Case studies: Drones, warehouse robots, smart agriculture robots; Mini-project discussion: IoT-controlled robot

Program Elective: Programming for IoT Boards

155704

Unit 1.0: IoT Ecosystem and Enabling Technologies

IoT Ecosystem, Challenges and Levels of Implementation, Enabling Technologies • Overview of Processing Elements and Peripherals

Unit 2.0: Programming for Prototyping Boards

Environment: Board, IDE, shields • Programming: syntax, variables, types, operators, constructs and functions • Sketch: skeleton, compile and upload, accessing pins • Debugging: UART communication protocol and serial library

Unit 3.0: Interfacing with Prototyping Boards

Circuits: design, wiring, passive components • Sensors and Actuators: Interfacing, Read/Write • Software libraries; Shields - interfacing and libraries

Unit 4.0: Single Board Computers: Programming & Interfacing

SBC Architecture & Schematic Board schematic • Setup, Configure & Use, OS implications: Linux - basics, file system and processes, Shell CLI & GUI • Programming APIs - RPi. GPIO - PWM library to access pins - Tkinter GUI

Unit 5.0: IoT Networking, Protocols & Cloud Integration

Networking & Internet Connectivity, Standard Internet Protocols - MQTT & CoAP • Networking Socket Interface - Cloud - Public APIs and SDK's for accessing cloud services • Social Network APIs - Interfacing - sensors and actuators - Pi Camera, Servo - APIs for data conversion

Unit 6.0: Embedded Programming and RTOS

Embedded Programming: MCU, GPIO, WDT, timers/counters - I/O - A/D - D/A, PWM, Interrupts, Memory; serial communication UART - I2C - SPI, Peripheral Interfacing • OS - basics - types - tasks - process - threads (POSIX Threads), thread preemption - Preemptive Task Scheduling Policies - Priority Inversion - Task communication - Task Synchronization issues - racing and deadlock - binary and counting semaphores (Mutex example) - choosing RTOS • Real World Projects: IoT Integrated Primary Health Care, Face Detection by AI, Cloud IoT Systems for Smart Agriculture, Smart Home Gadgets, Autonomous Car Features, Speed and horn intensity control

Program Elective: Pattern Recognition

155705

Unit 1.0: Introduction

Introduction fundamentals and definitions, Feature vectors, Classifiers, Supervised and Unsupervised learning, Bayesian decision theory

Unit 2.0: Features

Types and traits, scaling ordering, measurements, normalization, invariance, feature properties • Dimensionality reduction of feature space, dimensionality reduction by feature selection, PCA, KPCA, ICA

Unit 3.0: Parameter estimation

Maximum likelihood estimation (MLE), least squares estimation (LSE), Method of minimum variance & unbiased Estimation (MVUE); parameter free methods: KNN, Clustering • Special classifiers: linear regression, LDA, SVM, CNN

Unit 4.0: Classifiers and learning

Fundamentals of classifiers, Linear Classifiers, Nonlinear Classifiers. Unsupervised and semi supervised learning: Learning from unclassified data, Characteristics analysis of different classifiers

Unit 5.0: Clustering

Basic Concepts of clustering, Hierarchical agglomerative clustering, K-means partitional clustering, semi supervised learning with expectation maximization using labelled and unlabelled data

Unit 6.0: Classification and Ensemble Learning Techniques

Classification with nominal features : decision tree, random forest; classifier independent concepts, Combinations of classifiers: boosting, voting, stacking

Program Elective: Sensors and Actuator Devices for IoT

155706

Unit 1.0: Introduction to Sensors

Principles of sensing, classification and characteristics, Static and dynamic parameters, Environmental Parameters (EP), Sensor Characterization • Electromechanical Sensors: Introduction, Resistive Potentiometer, Strain Gauge, Resistance Strain Gauge, Semiconductor Strain Gauges • Inductive Sensors: Sensitivity and Linearity of the Sensor, Types; Capacitive Sensors: Electrostatic Transducer, Force/Stress Sensors Using Quartz Resonators, Ultrasonic Sensors

Unit 2.0: Thermal and Magnetic Sensors

Thermal Sensors: Gas Thermometric Sensors, Thermal Expansion Type Thermometric Sensors, Acoustic Temperature Sensor, Dielectric Constant and Refractive Index Thermosensors, Helium Low Temperature Thermometer, Nuclear and Magnetic Thermometer, Resistance Change Type Thermometric Sensors, Junction Semiconductor Types • Magnetic Sensors: Working Principles, Types and Characteristics, Force & displacement Sensors

Unit 3.0: Radiation Sensors

Radiation Sensors: Introduction, Basic Characteristics, Types of Photoresistors /Photodetectors, X-ray and Nuclear Radiation Sensors, Fiber Optic Sensors

Unit 4.0: Smart Sensors & Interfacing

Introduction, Primary Sensors, Excitation, Amplification, Filters, Converters (ADC/DAC), Compensation, Information Coding and Processing, Data Communication, Standards for Smart Sensor Interface, Sensor Nodes & Automation Interfaces

Unit 5.0: Sensors Applications

On-board Automobile Sensors, Home Appliance Sensors, Medical Diagnostic Sensors, Sensors for Manufacturing, Environmental Monitoring Sensors

Unit 6.0: Actuators

Pneumatic and Hydraulic Actuation Systems, Valves and Rotary actuators, Mechanical Actuation Systems, Electrical Actuation Systems (Solenoids, Motors, Relays)

Open Elective-I

1557XX
Theory Course • Course Details
View PYQ Papers
Available Elective Tracks & Options (5):

Open Elective: Soft Skills and Interpersonal Communication

100728

Unit 1.0: Self-Discovery and Analysis

Self-Analysis: SWOT Analysis, Who am I, Attributes, Importance of Self-Confidence, Self-Esteem

Unit 2.0: Creative and Innovative Thinking

Creativity: Out of Box Thinking, Lateral Thinking

Unit 3.0: Attitude and Motivation

Attitude: Factors Influencing Attitude, Challenges and Lessons from Attitude, Etiquette • Motivation: Factors of Motivation, Self-Talk, Intrinsic & Extrinsic Motivators

Unit 4.0: Strategic Goal Setting

Goal Setting: Wish List, SMART Goals, Blue Print for Success, Short Term, Long Term, Life Time Goals

Unit 5.0: Effective Time Management

Time Management: Value of Time, Diagnosing Time Management, Weekly Planner, To Do List, Prioritizing Work

Unit 6.0: Interpersonal Skills and Teamwork

Interpersonal Skills: Gratitude - Understanding the relationship between Leadership Networking & Team work. Assessing Interpersonal Skills Situation description of Interpersonal Skill • Team Work - Necessity of Team Work Personally, Socially and Educationally

Open Elective: Introduction to VLSI Design

100729

Unit 1.0: Introduction MOSFET, threshold voltage, current, Channel length modulation, body bias effect and short channel effects, MOS switch, MOSFET capacitances, MOSFET models for calculation- Transistors and Layout, CMOS layout elements, parasitics, wires and vias- design rules- layout design SPICE simulation of MOSFET I-V characteristics and parameter extraction

Unit 2.0: CMOS inverter, static characteristics, noise margin, effect of process variation, supply scaling, dynamic characteristics, inverter design for a given VTC and speed, effect of input rise time and fall time, static and dynamic power dissipation, energy & power delay product, sizing chain of inverters, latch up effect- Simulation of static and dynamic characteristics, layout, post layout simulation

Unit 3.0: Static CMOS design, Complementary CMOS, static properties, propagation delay, Elmore delay model, power consumption, low power design techniques, logical effort for transistor sizing, ratioed logic

Unit 4.0: Pseudo NMOS inverter, DCVSL, PTL, DPTL & Transmission gate logic, dynamic CMOS design, speed and power considerations, Domino logic and its derivatives, C2MOS, TSPC registers, NORA CMOS - Course project

Unit 5.0: Circuit design considerations of Arithmetic circuits, shifter, CMOS memory design - SRAM and DRAM

Unit 6.0: BiCMOS logic - static and dynamic behaviour - Delay and power consumption in BiCMOS Logic

Open Elective: Sales and Marketing

100734

Unit 1.0: Introduction to Sales and Marketing

Marketing: Definition, importance, and evolution of marketing concepts • Sales: Definition, role of sales in a business, and the relationship between sales and marketing • Marketing Mix (4Ps): Product, Price, Place (Distribution), and Promotion • Consumer Behavior: Understanding consumer motivations, buying decisions, and factors influencing purchasing

Unit 2.0: Market Analysis and Strategy

Market Segmentation, Targeting, and Positioning (STP): Identifying target markets, developing positioning strategies • Market Research: Understanding the purpose of market research, types of research methods, and data analysis • Competitive Analysis: Identifying competitors, analyzing their strengths and weaknesses, and developing competitive strategies • Strategic Marketing Planning: Developing marketing plans, setting objectives, and measuring performance

Unit 3.0: Sales Management and Techniques

Sales Processes and Strategies: Understanding different sales strategies, lead generation, and sales techniques • Sales Force Management: Recruiting, training, motivating, and managing sales personnel • Customer Relationship Management (CRM): Understanding the importance of CRM, managing customer interactions, and building strong relationships • Sales Communication and Negotiation: Developing effective communication skills, negotiation techniques, and closing sales

Unit 4.0: Marketing Communication and Promotion

Advertising: Understanding different advertising media, campaign planning, and media buying • Sales Promotion: Understanding different types of sales promotions, couponing, and loyalty programs • Public Relations (PR): Building positive relationships with the public, media relations, and crisis communication • Digital Marketing: Understanding online marketing channels, social media marketing, SEO, and email marketing

Unit 5.0: Product, Branding, and Pricing Strategies

Product and Brand Management: Developing and managing product lines, branding strategies, and brand equity • Pricing Strategies: Understanding different pricing methods, pricing objectives, and pricing policies

Unit 6.0: Distribution Channels and Ethics in Sales & Marketing

Distribution Channels: Understanding different distribution channels, logistics, and supply chain management • Ethics in Sales and Marketing: Understanding ethical issues in sales and marketing, and responsible marketing practices

Open Elective: Digital Signal Processing

100735

Unit 1.0: Discrete-time signals and systems

Discrete time signals and systems: Sequences; representation of signals on orthogonal basis; Representation of discrete systems using difference equations, Sampling and reconstruction of signals - aliasing; Sampling theorem and Nyquist rate

Unit 2.0: Z-transform

Z-Transform, Region of Convergence, Analysis of Linear Shift Invariant systems using z-transform, Properties of z-transform for causal signals, Interpretation of stability in z-domain, Inverse z-transforms

Unit 3.0: Discrete Fourier Transform

Frequency Domain Analysis, Discrete Fourier Transform (DFT), Properties of DFT, Convolution of signals, Fast Fourier Transform Algorithm, Parseval's Identity, Implementation of Discrete Time Systems

Unit 4.0: Design of Digital filters

Design of FIR Digital filters: Window method, Park-McClellan's method. Design of IIR Digital Filters: Butterworth, Chebyshev and Elliptic Approximations; Low-pass, Bandpass, Band-stop and Highpass filters

Unit 5.0: Effect of finite register length in FIR filter design, Parametric and non-parametric spectral estimation. Introduction to multi-rate signal processing

Unit 6.0: Applications of Digital Signal Processing

Correlation Functions and Power Spectra, Stationary Processes, Optimal filtering using ARMA Model, Linear Mean-Square Estimation, Wiener Filter

Open Elective: Control System

100736

Unit 1.0: Discrete Representation of Continuous Systems

Basics of Digital Control Systems. Discrete representation of continuous systems. Sample and hold circuit. Mathematical Modelling of sample and hold circuit. Effects of Sampling and Quantization. Choice of sampling frequency. ZOH equivalent

Unit 2.0: Discrete System Analysis

Z-Transform and Inverse Z Transform for analyzing discrete time systems. Pulse Transfer function. Pulse transfer function of closed loop systems. Mapping from s-plane to z plane. Solution of Discrete time systems. Time response of discrete time system

Unit 3.0: Stability of Discrete Time System

Stability analysis using Jury test, Stability analysis using bilinear transformation, Design of digital control system with dead beat response, Practical issues with dead beat response design

Unit 4.0: State Space Approach for discrete time systems

State space models of discrete systems, State space analysis. Lyapunov Stability. Controllability, reach-ability, Re-constructibility and observability analysis. Effect of pole zero cancellation on the controllability & observability

Unit 5.0: Design of Digital Control System

Design of Discrete PID Controller, Design of discrete state feedback controller. Design of set point tracker. Design of Discrete Observer for LTI System. Design of Discrete compensator

Unit 6.0: Discrete output feedback control

Design of discrete output feedback control. Fast output sampling (FOS) and periodic output feedback controller design for discrete time systems

Deep Learning Lab

155701P
Laboratory Subject • 1 Units
View PYQ Papers

Topics Part 1

  • Write a program to implement a single-layer perceptron for binary classification
  • Build an MLP classifier using a custom forward pass and backpropagation
  • Implement Backward propagation neural network
  • Implement Gradient Descent, SGD, and Momentum on a simple function and plot convergence
  • Write a program to perform manual convolution on an image using a custom filter (edge detection / blur)
  • Build a CNN on MNIST / CIFAR-10 using PyTorch or TensorFlow
  • Train, test, and report accuracy
  • Use a pretrained model (VGG16 / ResNet50) and fine-tune it on a small dataset
  • RNN / LSTM for Text Generation, sentiment analysis
  • Implement LSTM-based text generation on a small text corpus (e.g., nursery rhymes)
  • Build a Denoising Autoencoder to remove noise from images (MNIST/CIFAR-10)

Prescribed Experiments

  1. Write a program to implement a single-layer perceptron for binary classification
  2. Build an MLP classifier using a custom forward pass and backpropagation
  3. Implement Backward propagation neural network
  4. Implement Gradient Descent, SGD, and Momentum on a simple function and plot convergence
  5. Write a program to perform manual convolution on an image using a custom filter (edge detection / blur)
  6. Build a CNN on MNIST / CIFAR-10 using PyTorch or TensorFlow
  7. Train, test, and report accuracy
  8. Use a pretrained model (VGG16 / ResNet50) and fine-tune it on a small dataset
  9. RNN / LSTM for Text Generation, sentiment analysis
  10. Implement LSTM-based text generation on a small text corpus (e.g., nursery rhymes)
  11. Build a Denoising Autoencoder to remove noise from images (MNIST/CIFAR-10)

Summer Entrepreneurship – III

100707
Laboratory Subject • Course Details
View PYQ Papers

Project-I

100709P
Laboratory Subject • Course Details
View PYQ Papers