International School of Engineering
2nd Floor, Jyothi Imperial, Vamsiram Builders
Gachibowli, Hyderabad – 500032 INDIA
PGP in Data Science
Total credits: 15 (core + electives)
Module 1: Foundations of Probability and Statistics for Data Science
Credits: 1
• Descriptive statistics
• Probability and types of probabilities
• Bayes Theorem
• Probability distributions
• Central Limit Theorem
• Inferential statistics: Confidence Intervals, Hypothesis Testing
• Statistical tests
Module 2: Essential Engineering Skills in Data Analytics Using R and Python
Credits: 1
• Overview of the Data Science field
• Basics of the language
• Data manipulation
• Machine Learning
• Data Science Pipeline
Module 3: Statistics and Probability in Decision Modeling
Credits: 3
• Simple Linear Regression
• Multiple Linear Regression
• Logistic Regression
• Naïve Bayes Classifier
• Bias-variance trade-off
• L1, L2 and Elastic-net Regularization
• Dimensionality reduction using Principal component Analysis
• Time Series Forecasting
Module 4: The Art and Science of Storytelling with Data Visualizations
Credits: 1
• Thought process for building effective visualizations (Video lecture)
• Advanced data visualization using R, Python and Tableau
Module 5: Methods and Algorithms in Machine Learning
Credits: 3
• Association Rules
• Decision Trees
Inspire…Educate…Transform.
International School of Engineering
2nd Floor, Jyothi Imperial, Vamsiram Builders
Gachibowli, Hyderabad – 500032 INDIA
• K-Means Clustering and hierarchical clustering
• K-Nearest Neighbours classifier and regression
• Collaborative filtering
• Support Vector Machines
• Bagging and Boosting methods: Random Forest, Gradient Boosting, Xgboost
Module 6: AI and Decision Sciences
Credits: 1
• Linear Programming
• Monte Carlo Simulations
• Genetic Algorithm
• Artificial Neural Networks
• Deep learning
Module 7: Design Thinking and Research
Credits: 1
• Systems and Design thinking principles and frameworks
• Business aspects that are important for solving and implementing data science
solutions.
• State of the art of data science, problem definition, data strategy, performance
metrics and productionization strategies.
• Develop a blueprint of the solution for a problem of choice.
Module 8: Deploying AI/ML solution on cloud and on-premise
Credits: 1
• Overview of Dockers, need for Docker and REST API
• Docker with Python and MySQL
• About RestAPI and Flask in Python
• GUnicorn and Nginx for productionize the Rest API code
• Scalability using Kubernetes
Module 9: Transformation through Trance Formation
Credits: 1
• Psychology of Growth Mindset
• Living a Self-Directed life
• Circle of Excellence – Restructuring Confidence
• Building Unconscious Rapport and beyond.
• Reaching and staying at Peak Performance
• The Success Model
• The Art of Calibration
• The Art of Framing and Re-framing
Inspire…Educate…Transform.
International School of Engineering
2nd Floor, Jyothi Imperial, Vamsiram Builders
Gachibowli, Hyderabad – 500032 INDIA
Electives (2 mandatory)
Credits: 1 for each elective
Reinforcement learning:
• Introduction to RL and Markov decision processes (MDP), Dynamic programming for
solving an MDP.
• Analysis of simple toy use-cases and RL problem formulation. Formulating a use-case
(eg. resource management) as a reinforcement learning problem and solving it using
DP.
• Model-free prediction: Monte-Carlo and Temporal-Difference learning. Model-free
control: On-policy and Off-policy learning, On-policy MC and TD, Sarsa, Q-learning.
DQN (Deep Q Networks)
• Formulating a use-case (eg. trading/portfolio management) as a reinforcement
learning problem and solving it using Q-learning.
Introduction to Computer vision and applications:
• Basics of computer vision: image as a n-dimensional matrix, color spaces, filtering,
feature extraction (wavelets, SIFT etc.).
• Image processing and keypoint extraction in OpenCV. Image classification using
traditional computer vision.
• Convolutional neural networks, popular CNN architectures (ResNet, Inception, etc.),
data augmentation, architectural hyper-parameters.
• Visual image recognition and its applications in different domains. Types of
convolution operations and model compression.
Foundations of Text mining and Natural Language Processing I
• Text Mining, Text pre-processing, Information retrieval, Topic Modeling
• Text summarization (extractive), Text classification and Sentiment analysis.
Foundations of Text mining and Natural Language Processing II
• First step towards NLP: unstructured to structured Embeddings. CNN for text.
• Recurrent neural networks, LSTM and GRU models. NLP based text classification,
Named entity recognition.
Foundations of IoT
• IoT evolution, several layers in the architectures, technical aspects of individual
components and what it involves
• Networking technologies, cloud vs edge
• IoT physical layer: Electronics, Sensors, microcontrollers and processing boards
• Demonstrating IoT capabilities using business applications
Inspire…Educate…Transform.
International School of Engineering
2nd Floor, Jyothi Imperial, Vamsiram Builders
Gachibowli, Hyderabad – 500032 INDIA
Operations Research for Industry 4.0
• Math refresher: Matrix, vector notation; Multivariate functions: Partial derivatives,
Gradient, Hessian, Jacobian, Eigenvalues: basic understanding and intuition
• Basics of optimization: Unconstrained, constrained optimization. A basic
understanding of single and multi-objective optimization, Convex functions,
Quadratic form
• Function minimization: Gradient descent
• Advanced examples in Linear Programming
Blockchain
• Historical context and how the field evolved. Technology aspects of Blockchain,
Distributed ledger technology versus Blockchain, architectural overview of
permission and permissionless Blockchain. Smart Contract in Ethereum & Chain
Code in Hyperledger fabric
• Applications in context of business network, various other networks, tools and
engagement models. Overview of business applications to understand the workflow
and data generated.
An Overview of Big Data and Hadoop Ecosystem
• Introduction to the Big Data explosion
o Big Data Ecosystem components
o Capacity planning
o High Level Architecture
• Analysing Structured and Semi-structured Data using NoSQL
o Cluster intro
o Linux commands
o Distributed storage with HDFS
o YARN as the resource manager
o High Level intro to MR2
Bootcamp and Mindcamp
• This module will consist of Bootcamps and Mindcamps that are intense programming
and personality development sessions
• A typical day in a bootcamp would consist of hands-on programming focussed on
either deep dive into an ML algorithm or using these algorithms to participate in an
online competition such as Kaggle. Coding session will be followed by 1-2 hours of
Mindcamp sessions (debates, discussions, role-playing, etc.) which will help students
build essential professional skills needed in the industry to complement the technical
skills learned in the bootcamp.
Inspire…Educate…Transform.
