IIT Roorkee Post Graduate Certificate Program in Data Science and Machine Learning

About Course

The IIT Roorkee Post Graduate Certificate Program in Data Science & Machine Learning is an executive course designed to equip professionals with the knowledge and skills required to excel in the field of data science and machine learning. This program is developed by IIT Roorkee, a premier institute of technology in India, and is aimed at working professionals who want to enhance their career prospects in this field. The course curriculum includes a combination of theoretical and practical sessions, providing students with a comprehensive understanding of the subject. The executive education program by IIT Roorkee is designed to be completed in 10 months, with a flexible schedule that allows students to balance their work and study commitments.

Learn about the foundations of Data Science
Introduction to Data Science Libraries like NumPy, Pandas and Matplotlib
Deployment of Machine Learning and Deep Learning
Different Machine Learning algorithms and its applications
Learn about Natural Language Processing
Learn to work with unstructured data
Application of the concepts taught in Program
Various Deep Learning Models built using Artificial Neural Network
Hands on experience of programming with TensorFlow

Course Content

Module 1: Foundations of Data Science and Generative AI
In this module, you will learn about foundations of Data Science. It is important that you are aware about the tools and technologies that are used for handling data. You will also learn about GenAI and its capabilities.

Emerging Technologies and AI
Understanding Data Science and AI
Generative AI

Module 2: Python for Data Science
This module will cover topics on data structures in Python including lists, tuples etc., loops, control structures, functions, NumPy, Pandas, MatplotLib. This module will help gain understanding of the Python programming language.

Module 3: Exploratory Data Analysis and Data Visualization
Exploring the data and understanding that it is a really important step even before we apply any Machine Learning models. Visualising the data helps to share the insight with all the stakeholders and helps in getting greater insights. You will be using Tableau for visualising the data.

Module 4: Machine Learning Algorithms
In this module, you will learn about different Machine Learning algorithms and their applications. You will get hands-on practice with your very first predictions using Machine Learning models.

Python ML Library – Scikit Learn
Introduction to ML- Types of Learning
Linear Regression
Logistic regression
K Nearest Neighbours
Naïve Bayes
Decision Trees
Support Vector Machines
Unsupervised Learning: Clustering & Dimensionality Reduction
Hands-on Case Studies for ML

Module 5: Advanced Machine Learning Concepts
Optimising the Machine Learning models is one of the key steps. You will learn about how to tune the hyper parameters of a model and get the desired outcome for a particular business problem.

Module 6: Text Analytics
Learn to work with the unstructured text data. Learn about how to extract meaningful insights from text data and prepare the data for Machine Learning models.

Module 7: Programming with TensorFlow, Neural Networks and Intro to Deep Learning
Get introduced to the concept of a neuron and how multiple neurons can be used to construct an Artificial Neural Network. Deep Learning is a class of Machine Learning algorithms that progressively extract features for better understanding of the problem. You will learn about various Deep Learning models built using Artificial Neural Networks.

Specialization 1: Deep Learning Applications with Image and Speech
One of the popular applications of Deep Learning is in image recognition and speech recognition. You will learn how to build complex image recognition and object detection models and apply them to solve business use cases.

Computer Vision with Open CV
Convolutional Neural Networks (CNN)
Pretrained CNN Models
Image Classification with KERAS
Object Detection
Hands-on Practice
Overview of Speech Recognition and Basic APIs
Advanced NLP – using Word Embeddings
Word2Vec, GLOVE
Working with sequence data – RNN and LSTM

Specialization 2: Data Engineering
Building the data pipelines and deploying the Machine Learning models are some of the important steps in implementing the DS and ML solutions in production. This module will help you learn these tools and techniques.

Introduction to Data Engineering & Big Data
Introduction to Hadoop, HDFS and map reduce
Data Analytics using Apache hive
Working with Cloud (Microsoft Azure)
Working with Apache Spark and Spark through databricks
Data /ingestion tools – Sqoop, Flume and Kafka
Working with NoSQL databases – Cassandra, Hbase and MongoDB
Introduction to Big data analytics with Spark ML
Implementing ML algorithms through spark ML

Module 9 – Self-paced Module: ML Ops
In this module you will learn about deploying the machine learning / deep learning modules using APIs on cloud.

Module 10: Capstone Project
End-to-end project to apply the concepts taught in the program.

Creating a Hierarchical Classification Tool for COVID-19 Literature
Patch Classification from Image Labels – Healthcare
Fraud Analysis Using ML Algorithms
Enabling Business Intelligence for a Restaurant Aggregator
Land Use classification based on Satellite Imagery
Retail Customer Segmentation
Telecom Customer Churn
Data Quality and Data Exploration of Credit Card Dataset
Chatbot using DialogFlow
Lung Cancer Detection
Bone Age using X-Ray Images
Bank Loan Portfolio Data Pre-processing
Taxi Trip Data Analysis
COVID-19 Data Analysis
COVID Vaccination Helpline- Customised Chatbot using Alexa Blueprint
Prediction of COVID-19 spread using Time Series with LSTM

Mini Projects and Case Studies

IPL Analytics
eBay Car Sales Analytics
E-commerce Customer Shopping Analytics
Classification of Human Activity Recognition
Predictive model to forecast the sales of supermarket
Customer Segmentation of Clickstream Online Retail Shopping Data
Popularity Prediction of Social Media Articles
Bitcoin Price Prediction
Time Series Analysis of Energy Consumptions of Appliances
Ensemble Techniques to Classify the Customer Churn
Regularisation Techniques for IPL Auction Analysis
Story telling with Netflix Text Data
Topic Modelling on Amazon Review Dataset
Personality Classification based on MBTI Metric
Fake News Detection
Auto tagging of photos uploaded by the users on review website
COVID-19 Detection Using Chest X Rays

About Course

What Will You Learn?

Course Content

Module 1: Foundations of Data Science and Generative AI In this module, you will learn about foundations of Data Science. It is important that you are aware about the tools and technologies that are used for handling data. You will also learn about GenAI and its capabilities.

Emerging Technologies and AI

Understanding Data Science and AI

Generative AI

Module 2: Python for Data Science This module will cover topics on data structures in Python including lists, tuples etc., loops, control structures, functions, NumPy, Pandas, MatplotLib. This module will help gain understanding of the Python programming language.

Sourcing Data from Different Sources

Data Wrangling

Cleaning Date and Text Columns

Exploratory Data Analysis

Working with SQL

Data Visualization using Tableau

Module 4: Machine Learning Algorithms In this module, you will learn about different Machine Learning algorithms and their applications. You will get hands-on practice with your very first predictions using Machine Learning models.

Python ML Library – Scikit Learn

Introduction to ML- Types of Learning

Linear Regression

Logistic regression

K Nearest Neighbours

Naïve Bayes

Decision Trees

Support Vector Machines

Unsupervised Learning: Clustering & Dimensionality Reduction

Hands-on Case Studies for ML

Module 5: Advanced Machine Learning Concepts Optimising the Machine Learning models is one of the key steps. You will learn about how to tune the hyper parameters of a model and get the desired outcome for a particular business problem.

Hyper Parameter Tuning

Overfitting and Regularisation

Ensemble Models

Gradient Boosting Machines

Feature Engineering & Feature Selection Techniques

Time Series Forecasting

Module 6: Text Analytics Learn to work with the unstructured text data. Learn about how to extract meaningful insights from text data and prepare the data for Machine Learning models.

Text Analytics Overview

Sentiment Analysis on Text Data

Naïve-Bayes Model for Sentiment Classification

Document Summarisation

Topic Modeling

Hands-on Practice

Fundamentals of Tensorflow

TensorFlow Programming Model

Performing basic operations using TensorFlow

Introduction to Perceptron

Perceptron Training

Deep Neural Networks

Keras API

Specialization 1: Deep Learning Applications with Image and Speech One of the popular applications of Deep Learning is in image recognition and speech recognition. You will learn how to build complex image recognition and object detection models and apply them to solve business use cases.

Computer Vision with Open CV

Convolutional Neural Networks (CNN)

Pretrained CNN Models

Image Classification with KERAS

Object Detection

Hands-on Practice

Overview of Speech Recognition and Basic APIs

Advanced NLP – using Word Embeddings

Word2Vec, GLOVE

Working with sequence data – RNN and LSTM

Specialization 2: Data Engineering Building the data pipelines and deploying the Machine Learning models are some of the important steps in implementing the DS and ML solutions in production. This module will help you learn these tools and techniques.

Introduction to Data Engineering & Big Data

Introduction to Hadoop, HDFS and map reduce

Data Analytics using Apache hive

Working with Cloud (Microsoft Azure)

Working with Apache Spark and Spark through databricks

Data /ingestion tools – Sqoop, Flume and Kafka

Working with NoSQL databases – Cassandra, Hbase and MongoDB

Introduction to Big data analytics with Spark ML

Implementing ML algorithms through spark ML

Module 9 – Self-paced Module: ML Ops In this module you will learn about deploying the machine learning / deep learning modules using APIs on cloud.

ML Model Lifecycle

Flask API Deployment

Fast API Deployment

Non-API deployment

Deploying models on AWS & Azure

PySpark API

Module 10: Capstone Project End-to-end project to apply the concepts taught in the program.

Creating a Hierarchical Classification Tool for COVID-19 Literature

Patch Classification from Image Labels – Healthcare

Fraud Analysis Using ML Algorithms

Enabling Business Intelligence for a Restaurant Aggregator

Land Use classification based on Satellite Imagery