AI Lessons
Lesson 23: Neural networks - How AI learns patterns

Purpose: How AI learns patterns from data and improves its predictions through feedback.

No. of Classes

1 - (Time : 1 hour 30 minutes, Laptops/desktops : 10, Students strength : 15 to 20).

Materials Required

Laptop / Desktop with Internet connections / Wi-Fi.

Curriculum Content

2. AI and ML Concepts - A Simplified Overview

  • 2.10 Neural networks
Prior knowledge
  • Understanding that AI recognizes images, speech, and text by learning from data
  • Basic familiarity with inputs, outputs, and pattern recognition
Exercises

Exercise (1)


  • Play a rule-guessing game to identify a hidden pattern. Learn how neural networks improve their predictions by learning from feedback.

Exercise (2)


Solutions



Teacher's Instruction:
  1. Emphasize the terms: neural networks, weights, input and output layers, hidden layers.
  2. Explain that machines learn through trial, error, and feedback.
  3. Highlight that neural networks discover patterns in data rather than following rigid, hand-coded rules.
  4. Points to Ponder:
    • Humans can learn what a zebra is after seeing just one picture, but a neural network needs thousands of zebra images. Why do you think artificial neural networks need so much more data than humans to learn a simple concept?