ML Resources

From Code to Model - Comprehensive ML materials for students and instructors

Course Offerings

Complete ML courses from IIT Gandhinagar with video lectures, assignments, and proven pedagogical approaches.

Explore Courses

Interactive Slides

Professional LaTeX-based lecture slides with mathematical rigor and clear explanations of ML concepts.

View Slides

Comprehensive Tutorials

Step-by-step practice problems with detailed solutions to reinforce learning and build practical skills.

Browse Tutorials

Jupyter Notebooks

Interactive coding exercises and demonstrations with real datasets and implementations.

Explore Notebooks

Course Assignments

Real-world machine learning assignments from ES335 and ES654 courses with GitHub Classroom integration.

View Assignments

Course Overview

This comprehensive machine learning course provides a solid foundation in both theoretical concepts and practical applications. Students will learn to implement algorithms from scratch and apply state-of-the-art techniques to real-world problems.

What You’ll Learn

  • Supervised Learning: Linear/logistic regression, decision trees, SVMs, neural networks
  • Unsupervised Learning: Clustering, dimensionality reduction, anomaly detection
  • Model Evaluation: Cross-validation, bias-variance tradeoff, performance metrics
  • Advanced Topics: Ensemble methods, regularization, feature engineering
  • Practical Skills: Python implementation, data preprocessing, model deployment

Course Structure

Foundations
Mathematical prerequisites, data preprocessing, and basic ML concepts.

Math Review Python Basics

Supervised Learning
Regression and classification algorithms with hands-on implementation.

Linear Regression Logistic Regression Decision Trees SVMs

Advanced Methods
Ensemble methods, neural networks, and modern ML techniques.

Random Forest Neural Networks Deep Learning

Model Evaluation
Cross-validation, performance metrics, and model selection strategies.

Cross-Validation Bias-Variance Metrics

Getting Started

  1. Prerequisites: Basic linear algebra, calculus, probability, and Python programming
  2. Setup: Install Python 3.8+, Jupyter, NumPy, pandas, scikit-learn, matplotlib
  3. Materials: All slides, tutorials, and notebooks are available on this website
  4. Practice: Work through tutorials and implement algorithms in the provided notebooks
Pro Tip

Start with the mathematical foundations in our tutorials, then work through the interactive notebooks to see concepts in action!

About These Materials

These comprehensive machine learning resources have been developed and refined over several years, combining theoretical foundations with practical implementations. The content emphasizes both conceptual understanding and hands-on coding skills.

The collection includes over 100 interactive Jupyter notebooks, comprehensive lecture slides, and detailed tutorials designed for both students and instructors. All materials are continuously updated to reflect current best practices in machine learning education.

Contributing & Feedback

Found an issue or have a suggestion? We welcome contributions from the community!

For questions or feedback, visit Prof. Nipun Batra’s homepage or create an issue