Course Outline: Modules 1 to 25
Module 1: Introduction to the Programme
Overview of topics to be covered in the Programme
Motivation for the Programme
Overview of the Programme
Expected Outcomes of the Programme
Brief about software/tools
Module 2: Mathematics Fundamentals
Linear Algebra: Vectors, matrices, inner products, matrix-vector multiplication,
eigenvalues/vectors, singular value decomposition
Calculus: Differentiation (single/multiple variables, vectors, and matrices),
unconstrained and constrained optimisation (Lagrangian multiplier)
Probability Theory: Discrete and continuous random variables, probability
distributions, Bayes' rule, Gaussian density function, conditional probability
Statistics: Descriptive and inferential statistics, hypothesis testing, probability
distributions
Module 3: SQL Fundamentals
SQL Basics: RDBMS & NoSQL, MS SQL Server & MongoDB demos, SQL tables, joins,
subqueries, views, functions, pattern matching, UDFs, stored procedures, ranking,
sorting
Advanced SQL: Mathematical and date-time functions, SQL ROLLUP, record grouping,
common table expressions, clustered indexes
Data Pipeline Integration: Integrating ML models into data pipelines
Module 4: Python Fundamentals
Python: Pre-requisites: Python syntax, factors, NumPy, SciPy, Pandas, Data
Visualization, Scikit Learn, Python Multiprocessing, Seaborn, TensorFlow
Deployment and productionization
Advanced Python Techniques: Generators, iterators, decorators, context managers
Performance Optimization Techniques: Demo on Python types, Python packages,
Python C-extensions
Learn TensorFlow
Demo of deployment on Python
Demo on advanced Python techniques
Module 5: Exploratory Data Analysis (EDA)
Data types and variables; central tendency and dispersion
Five-point summary and skewness; box plot; covariance and correlation
Encoding, scaling, and normalization
Focus on preprocessing: missing values, working with outliers
Demo on EDA
Module 6: Applications of AI and ML
NLP and Text Processing Applications: Text classification, part-of-speech tagging,
named entity recognition, text summarization, question answering, matching,
translation
Demo on sentiment analysis, chatbot creation, text-to-text translation
Image and Video Processing Applications: Image classification, object detection, face
recognition, video captioning, visual question answering, virtual agent, game creation
Speech Processing Applications: Speech recognition, speaker recognition, speech
synthesis, speech-to-speech translation, spoken language recognition, text-to-speech
synthesis
Module 7: Paradigms of Machine Learning
Supervised learning
Unsupervised learning
Semi-supervised learning
Active learning
Self-supervised learning
Transfer learning
Domain adaptation
Zero-shot, One-shot, Few-shot learning
Federated learning
Module 8: Regression Methods
Linear model for regression
Supervised learning
Parameter estimation
Overfitting
Regularisation
Ridge regression
Module 9: Probabilistic Models for Classification
K-nearest neighbour classifier
Bayes classifier
Normal density function
Decision surfaces
Naive Bayes classifier
Maximum likelihood estimation
Gaussian mixture model
Module 10: Support Vector Machines for Classification
Distance of a point to a hyperplane
Margin of a separating hyperplane
Hard-margin SVM
Soft-margin SVM
Kernel functions
Multi-class classification using SVMs
Module 11: Dimension Reduction Techniques
Principal component analysis
Fisher discriminant analysis
Module 13: Ensemble Methods
Bagging
Boosting
AdaBoost
Applications of Ensemble Methods
Module 14: Clustering Techniques
K-Means Clustering
Hierarchical Clustering
Applications of Clustering Techniques
Module 15: Multilayer Feedforward Neural Networks for Classification and
Regression
McCulloch-Pitts Neuron
Perceptron Learning Rule
Sigmoid Activation Function
ReLU Activation Function
Softmax Activation Function
Multilayer Feedforward Neural Network
Error Backpropagation Method
Gradient Descent Method
Stochastic Gradient Descent Method
Stopping Criteria
Logistic Regression-Based Classifier
Focus: Deep Learning using TensorFlow and Keras, understanding feedforward neural
networks, backpropagation, gradient descent, and logistic regression
Module 16: Deep Feedforward Neural Networks
Generalized Delta Rule
Adam-Based Optimizer
Regularization Techniques: Dropout, Dropconnect, Batch Normalization
Module 17: Convolutional Neural Networks (CNNs)
Basic CNN Architecture
Rectilinear Unit (ReLU)
2D Deep CNNs: LeNet, VGGNet, GoogleNet, ResNet
Image Classification using 2D CNNs
3D CNN for Video Classification
Object Localization and Detection Algorithms – YOLO
Image Segmentation and UNet
Module 18: Recurrent Neural Networks (RNNs)
Architecture of an RNN
Unfolding an RNN
Backpropagation Through Time
Long Short-Term Memory (LSTM) Units
Gated Recurrent Units (GRUs)
Bidirectional RNNs
Deep RNNs
Module 19: Generative Adversarial Networks (GANs)
Structure of GAN
Types of GAN Models
Applications of GAN Models
Module 20: Transformers
Attention Mechanism
Transformer Architecture
BERT (Bidirectional Encoder Representations from Transformers)
VILBERT
GPT (Generative Pre-trained Transformer)
Applications of Transformer Models
Module 21: Applications of Generative AI
Applications of Gen AI in Different Domains
Examples of Prompt Engineering
Fine-Tuning
API Creation and Integration
Module 22: Reinforcement Learning
Markov Decision Processes (MDPs)
Q-Learning and Deep Q Networks (DQN)
Actor-Critic Models
Exploration vs. Exploitation Strategies
Module 23: Deployment of MLOps
Ethical Considerations (Banking, E-commerce Sectors)
Pushing Code to Repository
Responsible AI
Explainable AI
Registry, Model & Data Monitoring
Module 24: Cloud Deployment
Understanding Cloud Infrastructure Essentials
Cloud-Based ML Services and Databases
Containerization
Cloud Enablement – Scalability and Flexibility
Emerging Themes: FaaS, Edge Computing
Federated Learning
AutoML
Explainable AI
Cloud ML-Ops
Deployment on Gemma Models on Vertex AI and Kubernetes Engine
Scaling Using AWS
Module 25: Capstone Project
A comprehensive, real-world assignment where participants apply their knowledge and
skills to solve industry-specific problems
Integration of concepts from coursework, encouraging critical thinking and innovation
Hands-on experience to become industry-ready by tackling complex challenges in a
professional setting