Coming Soon
E2OECD AILit — Engaging with AI, Competency 2
How Does AI Work?
Learning from Data
AI doesn't think like humans. Instead, it learns patterns from data. Imagine teaching a child to recognize cats — you show them many pictures of cats until they can identify one on their own. AI works similarly: it sees thousands of examples and finds patterns.
Train Your Own AI
Sort these items into categories, then press Train to see how accurate your AI model is.
Click an item, then click a category
The Training Process
Training Data is the collection of examples you give the AI.
Labels tell the AI what each example is (e.g., “this is a cat”).
The Model finds patterns in the data and creates rules to make predictions.
Accuracy measures how often the model gets it right. More diverse, correctly labeled data = better accuracy.
Labels tell the AI what each example is (e.g., “this is a cat”).
The Model finds patterns in the data and creates rules to make predictions.
Accuracy measures how often the model gets it right. More diverse, correctly labeled data = better accuracy.
Garbage In, Garbage Out
If your training data is wrong or biased, the AI will learn wrong patterns. This is why data quality matters more than quantity.
Check Your Understanding
1. What does AI need to learn?
2. What happens if training data is biased?
3. What is 'accuracy' in AI?
Answer all questions. You need 70% to pass.