Term 1 · Foundations & the AI Project Cycle · Lesson 2 of 30All lessons
AI CourseSyllabax AI · Class 8Term 1 · Foundations & the AI Project Cycle
Term 1 · Foundations & the AI Project Cycle · Lesson 2

AI, Machine Learning and Deep Learning

5 min read30 practice questions15-question quiz

Learn how AI, Machine Learning and Deep Learning help computers think like us, with fun examples from cricket, YouTube and autos.

A friendly opening + what we'll learn

Hello, young explorer! Today we will discover three amazing friends – AI, Machine Learning and Deep Learning. We will see how they help your favourite cricket video, your YouTube playlist, and even the auto that takes you to school. By the end, you will know what each word means, how they are different, and how you can see them working around you. Let’s start this fun adventure together!

Core idea explained simply

AI is the big idea – a computer that can do tasks that need thinking, like recognizing faces or answering questions. Machine Learning is a way for AI to learn from examples, just like you practice maths problems to get better. Deep Learning is a deeper form of ML that uses many layers of tiny “neurons”, similar to how our brain has many layers of thoughts. Think of AI as a school, ML as the class you attend, and Deep Learning as the advanced club where you solve puzzles with many steps.

✦ The Big Idea

AI lets computers act smart; Machine Learning teaches them using data; Deep Learning adds many hidden layers for very complex learning.

Going a little deeper

Imagine you are scoring a cricket match. You write down every ball: runs, wickets, and overs. If you give this list to a computer, it can learn patterns – like which bowler gets more wickets in the last over. That learning is Machine Learning – the computer finds the pattern from the data you gave. Now, if you also give it pictures of each bowler’s action, the computer can use Deep Learning to recognise the bowler from a photo, even if the picture is blurry. So, more data and more layers mean the computer becomes smarter.

◆ Worked Example 1
  1. You ask Siri, “Play my favourite cricket highlights.”
  2. Siri sends your voice to a server.
  3. The server uses Machine Learning to understand the words “play”, “cricket”, and “highlights”.
  4. It looks up the video you often watch (training data).
  5. The video starts playing – Siri has predicted what you want.
  6. If you later tell Siri “Play more of this”, the system learns your new preference and updates its model.
◆ Worked Example 2
  1. An auto‑rickshaw driver uses an app that suggests the fastest route.
  2. The app collects past trips: distance, traffic, time of day (training data).
  3. Using Machine Learning, it finds patterns – e.g., roads near the market are busy at 5 pm.
  4. The app predicts the quickest path for today’s trip.
  5. As more drivers use it, the app gathers more data and its Deep Learning model becomes better at handling complex city maps.
📖 AI in the Real World

Riya loves watching dance videos on YouTube after school. One day, the app shows her a new video of a Bollywood dance that she has never seen, but it looks just like the ones she liked before. That’s AI at work! The system remembered the styles she enjoyed (training data) and used Machine Learning to suggest a video she would love. The next week, her voice assistant helps her set a reminder for the school’s cultural fest. Both moments show how AI, ML and Deep Learning quietly help us every day.

🧪 Try It Yourself
  1. Gather 5 different fruits (apple, banana, mango, orange, grapes).
  2. Write down one feature for each fruit – colour, size, taste.
  3. Shuffle the cards and ask a friend to pick a fruit.
  4. Using the features, try to guess the fruit – this is like Machine Learning (you use data to predict).
  5. Discuss how adding more features (like weight or smell) would make guessing easier – just like Deep Learning adds more layers.
💡 Remember
  • AI = computer that can think like us.
  • Machine Learning = learning from examples.
  • Deep Learning = many layers of learning, good for pictures and speech.
  • Training data helps the computer build a model.
  • Prediction is the computer’s guess after learning.
📝 Homework
  1. With a parent, list three places at home where you see AI (e.g., TV recommendations, voice assistant, smart lights).
  2. Ask your parent to show you one example of how the device learned your habit.
  3. Draw a simple picture of a model – you can use a brain shape and label it “My Computer’s Brain”.
  4. Write one sentence about what you think the computer will learn next.
✦ AI (Artificial Intelligence)✦ Machine Learning (ML)✦ Deep Learning✦ Training Data✦ Model✦ Prediction