Past tasks
Discord

A Guide to the International Olympiad in Artificial Intelligence

SOTA – AI Community · follows the IOAI 2026 Syllabus

Abstract

Start with the guide's introductory section, then follow the official IOAI syllabus topic by topic, in the order it lists them. Each module explains an idea, shows how to use it in code, and links resources and past olympiad tasks to practise on. Syllabus modules have a level, bronze, silver, gold or platinum, from the basics up to the most advanced topics. Getting Started has no level and stays visible when the sidebar shows one level at a time. Modules are written by the community; the ones that aren't ready yet show what each module will cover. Mark modules as you read them, and your progress is saved in this browser.

8 parts 61 modules 0 of 61 done

BBronze52 modules

Start here. The basics every contestant needs before attempting a task.

SSilver0 modules

Builds on bronze. The standard methods that most tasks are solved with.

GGold0 modules

Advanced and recent models, for contestants aiming at the top scores.

PPlatinum0 modules

Expert-level extensions and research frontiers beyond the core guide.

1Getting Started

0 of 9 done

1.1What is IOAI?

  1. 1.1.1 Introduction to the International Olympiad in Artificial Intelligence
  2. 1.1.2 IOAI Syllabus and Problem Areas

1.2How to Use This Guide

  1. 1.2.1 Guide Structure and Learning Path
  2. 1.2.2 How to Study and Practice Effectively

1.3Setting Up

  1. 1.3.1 Setting Up Python
  2. 1.3.2 Setting Up Jupyter Notebook

1.4What is INAIO?

  1. 1.4.1 Introduction to the Indian National AI Olympiad
  2. 1.4.2 Exam structure of various stages in INAIO

1.5How to Contribute

  1. 1.5.1 Contributing to the Guide

2Foundational Skills

0 of 4 done

2.1Python Basics

  1. 2.1.1 Python Fundamentals B
  2. 2.1.2 Object-Oriented Programming, Classes, and Inheritance B
  3. 2.1.3 Simple Python Problems B

2.2Jupyter Notebook

  1. 2.2.1 Jupyter Notebook Interface and Basics B

3Data Manipulation

0 of 2 done

3.1Data Manipulation Libraries

  1. 3.1.1 Pandas B
  2. 3.1.2 Matplotlib B

4Classical Machine Learning

0 of 16 done

4.1General Problem Setup

  1. 4.1.1 Terminology Used in Classical Machine Learning B
  2. 4.1.2 Structure of a Typical Classical Machine Learning Problem B

4.2Classical Machine Learning Preprocessing

  1. 4.2.1 Data Cleaning B

4.3Scikit-learn

  1. 4.3.1 Scikit-learn Basics B

4.4Classical Machine Learning Models

  1. 4.4.1 Linear Regression B
  2. 4.4.2 Logistic Regression B
  3. 4.4.3 K-Nearest Neighbors (K-NN) B
  4. 4.4.4 Decision Trees B
  5. 4.4.5 K-Means Clustering B

4.5Model Ensembles

  1. 4.5.1 Random Forests B
  2. 4.5.2 XGBoost B

4.6Classical Machine Learning Theory

  1. 4.6.1 Hyperparameter Tuning B
  2. 4.6.2 Underfitting and Overfitting B
  3. 4.6.3 Loss Functions B
  4. 4.6.4 Model Evaluation Metrics B
  5. 4.6.5 Cross-Validation B

5Deep Learning

0 of 12 done

5.1Tensor, Array, and Matrix Manipulation Libraries

  1. 5.1.1 NumPy Basics B
  2. 5.1.2 PyTorch Basics B

5.2Deep Learning Fundamentals

  1. 5.2.1 Multi-Layer Perceptrons B
  2. 5.2.2 Gradient Descent B
  3. 5.2.3 Backpropagation B
  4. 5.2.4 Tensors, Matrices, and Related Mathematical Functions B
  5. 5.2.5 Activation Functions B
  6. 5.2.6 Loss Functions B

5.3PyTorch Deep Learning Pipeline

  1. 5.3.1 Dataset and DataLoader B
  2. 5.3.2 A Simple MLP in PyTorch B
  3. 5.3.3 PyTorch Pipeline for a Simple Machine Learning Problem B
  4. 5.3.4 Simple Problem Examples B

6Computer Vision

0 of 7 done

6.1Image Modality Basics

  1. 6.1.1 Basic Image Terminology B

6.2Computer Vision Theory

  1. 6.2.1 Convolutional Layers B
  2. 6.2.2 Pooling B

6.3Raw Image Processing

  1. 6.3.1 Reading and Manipulating Images with Pillow B
  2. 6.3.2 Loading Images into Tensors with Torchvision B

6.4Computer Vision Models

  1. 6.4.1 Convolutional Neural Networks B
  2. 6.4.2 MNIST B

7Natural Language Processing

0 of 7 done

7.1Text Modality

  1. 7.1.1 Text Modality Basics B

7.2Text Processing

  1. 7.2.1 Text Preprocessing B
  2. 7.2.2 Tokenization B

7.3Basic NLP Algorithms

  1. 7.3.1 N-grams B
  2. 7.3.2 Vector Embeddings of Simple Text Features B
  3. 7.3.3 TF-IDF B
  4. 7.3.4 Bag of Words B

8Audio

0 of 4 done

8.1Audio Modality Basics

  1. 8.1.1 Waveforms, Sampling Rate, Duration, Amplitude, and Channels B
  2. 8.1.2 Theory of Audio Features B

8.2Librosa

  1. 8.2.1 Loading Audio with Librosa B
  2. 8.2.2 Audio Feature Extraction with Librosa B