Class 10 AI Unit 2: Advanced Concepts of Modeling in AI
18 theory hours · 7 practical hours · 11 theory marks
What this unit is about
The highest-scoring theory unit. It separates AI, machine learning and deep learning, compares rule-based and learning-based models, and splits machine learning into supervised (classification, regression), unsupervised (clustering, association) and reinforcement learning, ending with neural networks and CNNs.
Learn it with the AI tutor, one minute each
What the unit covers
- AI vs machine learning vs deep learning, and common terms used with data.
- Rule-based vs learning-based approaches.
- Supervised (classification, regression), unsupervised (clustering, association) and reinforcement learning.
- Deep learning: artificial neural networks (ANN) and convolutional neural networks (CNN), and how AI makes a decision.
Key terms
- Classification
- Supervised learning that predicts a category, such as spam or not spam.
- Regression
- Supervised learning that predicts a number, such as tomorrow's temperature.
- Clustering
- Unsupervised learning that groups similar items without labels.
- Association
- Unsupervised learning that finds items that occur together, such as products bought together.
- Reinforcement learning
- Learning by trial and error, guided by rewards and penalties.
Exam-style questions
1. Predicting a house price is classification or regression? Why?
Show answer →
Regression, because the output is a continuous number, not a category.
2. How is unsupervised learning different from supervised learning?
Show answer →
Supervised learning trains on labelled data; unsupervised learning gets no labels and finds structure, such as clusters, on its own.
3. Name the three types of layers in a neural network.
Show answer →
Input layer, hidden layer(s) and output layer.
Sources
Unit names, hours and marks checked against the official CBSE 2026-27 curriculum on 1 November 2026. Explanations and questions are written by CogniGuru.