Course Name Executive Certification in Advanced Data Science & Applications
Course Name as on
Certificate Executive Certification in Advanced Data Science & Applications
Certificate Type Certificate of Completion
Certificate Issued by IITM Pravartak Technology, Innovation Hub of Madras
• Provide a thorough introduction to the various methods in the field of
Artificial Intelligence, Deep Learning, Data Analytics, and its
mathematical foundations
Course Objectives • Provide strong hands on experience in both the mathematical and
computational aspects of Deep Learning
• Case studies through applications of the techniques to realistic data
from various business verticals
Qualification:
• Graduate/4-year Engineering Degree/B.Sc + M.Sc from a recognised
university (UGC/AICTE/DEC/AIU/State Government/recognised
international universities).
Eligibility
Minimum Experience:
• 3 years preferably in software engineering and/or other disciplines
involved in computational work.
• Must be comfortable with basic mathematics.
Pre Requisites
Target Segment
Module 1: Mathematical Preliminaries
Course Content Overview of the Course
• Overview of AI and ML
• The Mathematics required for AI and ML
Linear Algebra for AI
• Linear equations and solutions
• Vectors, Matrices and their Properties
• Inner Products and Norms
• Projections
• Eigenvalues and Eigenvectors
• Singular Value Decomposition
Probability and Statistics for AI
• Probability theory and axioms
• Random variables
• Probability distributions and density functions
• Expectations and moments
• Covariance and correlation
• Hypothesis testing
• MLE, MAP and Bayesian methods
Optimization for Data Science
• Multivariable Calculus
• Unconstrained optimization
• Introduction to least squares optimization
• Gradient based methods
Module 2: Computational Tools
Introduction to Python Programming
• Overview Python
• Setting up Python environment
Basics of Python
• Variables, Data Types
• Control flow (if-else statements, loops)
• Functions and Modules
Data Structures in Python
• List, Tuples
• Dictionaries, Sets
• Classes, Objects and Methods
Scientific computation with Python and its Libraries
• NumPy
• Pandas
• Scikit-learn library for ML
• Matplotlib for plotting and visualizations
Python for Deep Learning
• PyTorch
• TensorFlow and Keras
Module 3: Machine Learning: Foundations and Algorithms
• Foundations of Machine Learning – The Machine Learning Paradigm
• Linear and Polynomial Regression
• K-Nearest Neighbors
• Linear Classification – Logistic Regression
• Bias Variance tradeoff, Regularization
• Evaluation methods
Module 4: Deep Learning
• Recap of Linear and Logistic Regression
• Multiclass Classification
• Artificial Neural Networks
i. Artificial Neuron
ii. Multilayer Perceptron
iii. Universal Approximation Theorem
iv. Backpropagation in MLPs
v. Backprop on general graphs
• Optimization in Neural Networks
i. Gradient Descent and its Variants
ii. Momentum, Adam, etc.
iii. Batch Normalization and other techniques in modern Deep
Learning
• Basics of Hyper parameter optimization
• Convolutional Neural Networks (CNN)
i. Introduction
ii. CNN Operations
iii. CNN Training
iv. Image Recognition-SoTA model(s)
v. Object detection/localization - SoTA model(s)
vi. Semantic segmentation - SoTA model(s)
• Sequence Analysis Models
i. Recurrent Neural Networks (RNNs)
ii. Long Short Term Memory Networks (LSTMs)
Module 5: Generative models in Modern AI
• Introduction to Generative Models and their role in Modern AI
• Generative Adversarial Networks (GANs)
• Diffusion Models for image generation
• Transformer Architectures
• Large Language Models (such as ChatGPT)
i. Encoder only models
ii. Decoder only models
• Applications of existing Generative AI models
i. Leveraging tools such as ChatGPT in your context
• Future Trends in Generative AI
Pedagogy Case studies, industry projects and practical application
Assessment is based on weekly homework and exams on a regular intervals.
Assessment • 50% weightage to homework/case studies and 50% to the final exam.
• Attendance: 70% attendance is mandatory.
1. Prof. Ganapathy Krishnamurthi
Programme Faculty
2. Prof. Balaji Srinivasan
Duration 10 Months
Class schedule Sunday from 1.00 pm to 4.00 pm
On successful completion of the programme, you will get ‘Certificate of
Completion’ – “Executive Certification in Advanced Data Science and
Applications.”
Other Highlights:
• Highly recognised Certificate of Completion from IITM Pravartak
Programme • 2 days of Campus Immersion*
Highlights/USPs • The live programme is entirely taught by IIT Madras Faculty
• Peer-to-peer learning and mentoring from industry experts
• Pedagogy filled with case studies, industry projects & practical
application
• Industry-specific case studies
Total Fee INR 1,80,000/- + GST
Total Fees Total INR as applicable
Programme
Fee
