Welcome to the complete study material for Machine Learning and Applications. This section covers the foundational and mathematical principles of machine learning algorithms, their application to real-world problems across diverse domains, and emerging trends in the field including MLOps, explainability, and ethics.
The material is organised into three modules. Each module contains detailed notes, fully worked examples with step-by-step diagrams, and downloadable PDF notes prepared by Dr. Sanjiban Sekhar Roy.
Module 1: Introduction and Supervised Learning
Machine learning concepts and applications, hypothesis space and inductive bias, FIND-S and the Candidate Elimination Algorithm traced step by step on the EnjoySport dataset, model selection and evaluation, linear and non-linear regression, decision trees, K-nearest neighbour, and support vector machines.
Module 2: Probabilistic, Ensemble and Unsupervised Learning (coming soon)
Logistic regression and Bayesian learning, Naïve Bayes, Bayesian belief networks, artificial neural networks and backpropagation, bias–variance tradeoff, bagging, random forests, AdaBoost, clustering methods, PCA, LDA, and expectation maximization.
Module 3: Advanced Machine Learning Concepts (coming soon)
Self-supervised learning, reinforcement learning and the Q-learning algorithm, Markov decision processes, online learning, MLOps overview, explainability in machine learning, and ethics in ML.