22.3.1. Objective

Students will build a basic AI model using user-friendly tools. This project helps students understand the training and testing process, concept of datasets, and how machines learn patterns.

In this project, students will create a simple AI model, which is like teaching a computer how to recognize things, such as images, sounds, or words. The objective is to familiarize students with important concepts in AI, including how to collect data (datasets), how to train the AI to learn from this data, and how to test its accuracy. Just as a student learns from their homework and tests to improve their grades, the AI model improves by learning from the data it is trained on, which helps it recognize patterns effectively.

Think of it like teaching a child to identify fruits. You show them pictures of apples and oranges (the data), they hopefully learn to recognize the differences (training), and then you test their understanding by asking them to identify the fruits in new pictures (testing). Similarly, the AI learns from examples to become better at recognizing patterns.

1. Teachable Machine https://teachablemachine.withgoogle.com/ A web-based tool by Google that allows anyone to train a model using images, sounds, or poses.
2. Machine Learning for Kids https://machinelearningforkids.co.uk/ Designed especially for students to create and train models using text, images, or numbers and use them in Scratch or Python.

The project can be completed using user-friendly tools that make the process of building an AI model accessible to students. 'Teachable Machine' is a web tool that does not require any coding skills; students can simply upload images, sounds, or videos, and the software helps them create a model quickly. 'Machine Learning for Kids' is another platform tailored for educational purposes, allowing children to create AI models that can be integrated into programming environments like Scratch or Python.

Imagine using a cooking app that helps you prepare a dish. You enter ingredients and the app guides you step-by-step through the process. Similarly, these tools guide students through AI model-building without needing a complicated understanding of programming - like having a teaching assistant while learning how to cook!

1. Choose a type of data (Images/Text/Sound).
2. Collect sample data for different classes.
3. Train the model using the tool.
4. Test and refine the model.
5. Present the output and share your learning.

The project involves a series of steps that guide students from start to finish. First, they need to select what kind of data they wish to work with—this could be images, text, or sounds. Next, they will gather sample data, which means collecting enough examples for their chosen categories (like images of animals). After that, they will use the tool to train their AI model, which is where the model learns from the data. The testing phase allows students to check how well the model learned by running some tests to see if it can accurately identify or classify the data. Finally, students will present their findings, showcasing what they created and what they learned.

This process is similar to preparing for a test in school. First, you decide what subject to study, then gather textbooks and notes (data gathering), study the material (training), take a practice test (testing), and finally, when you're done, you present your project or discuss what you learned in class (presentation).

• Image Classifier: Recognize happy and sad faces. • Sound Classifier: Differentiate claps, whistles, and snaps. • Text Classifier: Identify positive or negative feedback.

For students to better understand what they can create, example projects are provided. An image classifier could be designed to distinguish between happy and sad faces based on facial expressions. A sound classifier would help differentiate between different noises such as claps, whistles, and snaps, and a text classifier would analyze text feedback to categorize it as positive or negative. These examples showcase practical applications of AI in recognizing visual and auditory patterns or sentiments.

Think about how social media platforms can recognize faces in photos or how voice assistants can differentiate commands. Just like a friend could tell the mood of another person based on their facial expression, AI can be trained to recognize these patterns through learning from data.

--