Evolve AI Institute | Free AI Education for All
Define the problem, choose your platform, identify categories
Gather 50+ diverse examples per category
Let the AI learn from your examples
Try your AI in different conditions, measure accuracy
Add more data, retrain, test again
Demonstrate and explain your AI project
Quick AI experiments
Image, sound, & pose recognition
Easiest to learn!
Build real mobile apps
AI-powered features
Create apps you can share!
Interactive games & stories
Creative AI projects
Most creative freedom!
Go to teachablemachine.withgoogle.com → Click "Get Started"
Select Image, Audio, or Pose Project based on your idea
Create 3-5 categories, record 50+ samples per class with variety
Click "Train Model" → Wait 1-3 minutes → Test in Preview panel
Go to appinventor.mit.edu → Sign in → Create New Project
Add Button, Camera, Image, Label components
Import "Personal Image Classifier" or "ImageBot" extension
Connect blocks: Button Click → Take Picture → Classify → Display Result
Go to scratch.mit.edu → Sign in → Click "Create"
Click "Add Extension" → Select "Video Sensing" or use ML for Kids
Go to machinelearningforkids.co.uk → Train custom model → Import to Scratch
Use ML blocks with game logic → Test → Share project online
Samples per category (minimum)
→ Add more diverse training samples
→ Check if categories are too similar
→ Remove poor quality samples
→ Simplify your categories
→ Add contrasting examples
→ Increase variety in those classes
→ Check background interference
→ Test in target environment
Solution: Collect minimum 50 samples per category
Solution: Vary angles, lighting, backgrounds, and positions
Solution: Ensure roughly equal samples for each category
Solution: Test in various lighting, angles, and environments
Solution: Embrace iteration - improvement takes multiple attempts!
Review project goals, choose platform, complete planning worksheet
Learn your chosen platform, understand interface and features
Gather diverse training samples for your categories
Train model, run initial tests, evaluate performance
Improve model based on testing, add features, polish interface
Present projects, gather feedback, reflect on learning
Begin with 3-4 categories, add more later if time allows
Don't wait until the end to test - catch problems early
Your teacher and classmates are resources - don't struggle alone
Regularly save progress to avoid losing your project
This is your chance to be creative - enjoy the process of creation
Check browser permissions, try different browser
Add more diverse data, simplify categories
Reduce sample count or image quality
Close other tabs, clear cache, restart browser
Check internet connection, try different format
Simplify scope, focus on core functionality
You're not just building an AI project - you're developing skills that will serve you throughout your career!
✓ Choose your platform
✓ Plan your project
✓ Start building!
You're about to become an AI creator!