Resources

Flagship Course

ML.AI

ML.AI 2026 was our summer course on Data Science and Machine Learning, offering a comprehensive blend of high-quality resources including videos, blogs, and weekly assignments, culminating in a hackathon to put everything into practice. The 6 week course took students from basic Python to complex neural networks. The course has now concluded — browse the full curriculum and resources on its dedicated page.

View ML.AI 2026 Course

Course Structure

6 weeks, basic Python to complex neural networks — ML.AI 2026 (concluded)

Python EDA Pandas NumPy

Week 1

Covers Python basics along with essential libraries like Pandas, NumPy, and Matplotlib, and introduces core concepts of Exploratory Data Analysis (EDA) and Feature Engineering.

Supervised Learning Model Performance Model Optimization

Week 2

Familiarises you with Machine Learning basics, covering Linear Regression, Logistic Regression, Regularization, Naive Bayes, Evaluation Metrics and more, along with the Sklearn library.

Advanced ML Unsupervised Learning Clustering

Week 3

Covers important ML algorithms like SVM, KMeans, and KNN, and introduces unsupervised learning, Principal Component Analysis (PCA), dimensionality reduction, clustering, and anomaly detection.

Ensemble Learning Kaggle Semi-Supervised Learning

Week 4

Covers Ensemble Learning and boosting algorithms like XGBoost, CatBoost, and LightGBM, along with semi-supervised approaches like self-training and label propagation.

Gradient Descent Activation Functions Backpropagation

Week 5

Starts your journey into neural networks and deep learning, covering the fundamentals of neural networks, activation functions, and backpropagation.

Hackathon

Participants put everything they learned to the test in the official Kaggle competition.

ML Playbook

  • Machine Learning & Deep Learning Fundamentals
  • Natural Language Processing and Large Language Models
  • Computer Vision and Vision Language Models
  • Reinforcement Learning and Deep RL
  • Generative AI, GANs, and Diffusion Models
  • Agentic AI and Model Context Protocol (MCP)
  • Graph Neural Networks, Explainable AI, and more

The IITG.ai ML Playbook is a curated roadmap designed to help students explore and master Machine Learning, Deep Learning, and modern AI technologies. It brings together high-quality learning resources from leading institutions and platforms covering the topics on the left.

This compilation is intended to serve as a structured guide for students interested in building strong foundations in AI and advancing towards research and industry-level expertise. The resource includes curated courses, lecture series, practical tutorials, and research roadmaps from platforms such as Stanford, Harvard, Hugging Face, Coursera, and other leading AI communities.

Open ML Playbook