AI & Machine Learning Worksheetsfor Kids & Beginners

Explore what AI means, how it differs from ordinary software, and where AI appears in everyday life — from voice assistants to recommendation engines.

Learn how machines learn from data instead of following hand-coded rules, and understand the core ML training loop with visual examples.

Discover how AI models learn from labeled examples (training data), and build intuition for why more and better data leads to smarter AI.

Understand the two key ingredients of supervised learning: features (the inputs AI looks at) and labels (the answers AI learns to predict).

Learn why we split data into training and testing sets, why testing on training data is cheating, and how the 80/20 split works in practice.

Build an intuitive understanding of classification by constructing a decision tree step-by-step — the foundation of many real ML algorithms.

Learn how to measure how well an AI model works — accuracy, correct/incorrect predictions, and how to build a confusion matrix.

Explore why AI can be biased, how biased training data causes unfair predictions, and what engineers do to build fairer AI systems.

Understand how AI recognises objects in images, how pixels become features, and how convolutional neural networks classify what they see.

Discover how chatbots and NLP AI understand text — from simple keyword matching to modern large language models like ChatGPT.

Write real Python code using scikit-learn to train a simple ML classifier, make predictions, and measure model accuracy hands-on.

Apply everything you have learned: define a problem, collect features and labels, train a model, evaluate it, and present your findings like an AI engineer.