← Design a tiny AI project lesson New set →

Build Your Own AI Project Worksheet

AI for students lesson 23: Design a tiny AI project · Set 838 · 40 questions
TalentJR

AI tip (Accuracy = correct ÷ total × 100): Steps: 1 choose a problem → 2 collect examples → 3 label them → 4 check and correct bad labels (clean the data) → 5 split into training and test sets → 6 train → 7 test with new examples → 8 measure accuracy → 9 improve the data and retest. Accuracy = correct ÷ total × 100. Wrong = total − correct. Expected right = accuracy ÷ 100 × total. Keep some examples apart for testing (for example one fifth); the rest are for training.

NameDateTime takenScore ___ / 40
  1. 1.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a louder speaker (b) a new colour screen (c) more labelled examples (d) fewer examples
  2. 2.🧪 You can plan a simple AI project with… (a) only a big robot (b) paper and examples (c) nothing at all (d) a secret password
  3. 3.🧪 Why must you test a model on examples it has NOT seen? (a) to make it faster (b) to see if it learned (c) to save paper (d) to make it bigger
  4. 4.🎯 Arjun’s bird-song app was tested on 25 new bird songs and got 21 right. What is its accuracy in percent?
  5. 5.📋 Planning an AI project: which comes first — train the model or work out the accuracy? (a) train the model (b) work out the accuracy
  6. 6.⚖️ Two leaf identifier models were tested on the same 10 leaf photos. Model A got 9 right and Model B got 7 right. How many percentage points more accurate is Model A?
  7. 7.⚖️ Two handwriting reader models were tested on the same 20 handwritten letters. Model A got 20 right and Model B got 19 right. How many percentage points more accurate is Model A?
  8. 8.⚖️ Two leaf identifier models were tested on the same 20 leaf photos. Model A got 18 right and Model B got 17 right. How many percentage points more accurate is Model A?
  9. 9.📋 Planning an AI project: which comes first — let it learn patterns or test on new photos? (a) let it learn patterns (b) test on new photos
  10. 10.🎯 Nisha’s bird-song app is 70% accurate. If it is tested on 50 new bird songs, how many should it get right?
  11. 11.🎯 Ananya’s recycling sorter is 90% accurate. If it is tested on 100 new waste photos, how many should it get right?
  12. 12.🎯 Kabir’s handwriting reader is 60% accurate. If it is tested on 30 new handwritten letters, how many should it get right?
  13. 13.🎯 Meera’s recycling sorter was tested on 10 new waste photos and got 5 right. What is its accuracy in percent?
  14. 14.❌ Ananya’s bird-song app was tested on 18 new bird songs and got 15 right. How many did it get wrong?
  15. 15.❌ Arjun’s handwriting reader was tested on 43 new handwritten letters and got 42 right. How many did it get wrong?
  16. 16.📋 Planning an AI project: which comes first — improve data, retest or tag each photo by type? (a) improve data, retest (b) tag each photo by type
  17. 17.📋 Planning an AI project: which comes first — test on new photos or train the model? (a) test on new photos (b) train the model
  18. 18.❌ Tara’s handwriting reader was tested on 36 new handwritten letters and got 34 right. How many did it get wrong?
  19. 19.🎯 Meera’s leaf identifier was tested on 10 new leaf photos and got 10 right. What is its accuracy in percent?
  20. 20.📦 Ananya collected 200 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  21. 21.📋 Planning an AI project: which comes first — fix it and test again or gather many examples? (a) fix it and test again (b) gather many examples
  22. 22.❌ Saanvi’s handwriting reader was tested on 42 new handwritten letters and got 36 right. How many did it get wrong?
  23. 23.📋 Planning an AI project: which comes first — choose what to sort or collect fruit photos? (a) choose what to sort (b) collect fruit photos
  24. 24.📋 Planning an AI project: which comes first — choose what to sort or work out the accuracy? (a) choose what to sort (b) work out the accuracy
  25. 25.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 23 right and Model B got 14 right. How many percentage points more accurate is Model A?
  26. 26.📦 Kabir collected 120 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  27. 27.📋 Planning an AI project: which comes first — fix it and test again or set aside test photos? (a) fix it and test again (b) set aside test photos
  28. 28.⚖️ Two recycling sorter models were tested on the same 20 waste photos. Model A got 15 right and Model B got 12 right. How many percentage points more accurate is Model A?
  29. 29.🎯 Tara’s bird-song app was tested on 10 new bird songs and got 9 right. What is its accuracy in percent?
  30. 30.🎯 Tara’s leaf identifier is 50% accurate. If it is tested on 100 new leaf photos, how many should it get right?
  31. 31.❌ Arjun’s leaf identifier was tested on 24 new leaf photos and got 20 right. How many did it get wrong?
  32. 32.⚖️ Two bird-song app models were tested on the same 10 bird songs. Model A got 7 right and Model B got 6 right. How many percentage points more accurate is Model A?
  33. 33.📋 Planning an AI project: which comes first — correct bad labels or pick a question to solve? (a) correct bad labels (b) pick a question to solve
  34. 34.🎯 Ishaan’s handwriting reader is 90% accurate. If it is tested on 60 new handwritten letters, how many should it get right?
  35. 35.📋 Planning an AI project: which comes first — train the model or improve data, retest? (a) train the model (b) improve data, retest
  36. 36.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 18 right and Model B got 14 right. How many percentage points more accurate is Model A?
  37. 37.📋 Planning an AI project: which comes first — correct bad labels or set aside test photos? (a) correct bad labels (b) set aside test photos
  38. 38.❌ Meera’s spam spotter was tested on 27 new messages and got 26 right. How many did it get wrong?
  39. 39.🎯 Arjun’s bird-song app was tested on 5 new bird songs and got 3 right. What is its accuracy in percent?
  40. 40.📋 Planning an AI project: which comes first — fix it and test again or recheck every label? (a) fix it and test again (b) recheck every label

Answer key

  1. more labelled examples
  2. paper and examples
  3. to see if it learned
  4. 84
  5. train the model
  6. 20
  7. 5
  8. 5
  9. let it learn patterns
  10. 35
  11. 90
  12. 18
  13. 50
  14. 3
  15. 1
  16. tag each photo by type
  17. train the model
  18. 2
  19. 100
  20. 160
  21. gather many examples
  22. 6
  23. choose what to sort
  24. choose what to sort
  25. 36
  26. 96
  27. set aside test photos
  28. 15
  29. 90
  30. 50
  31. 4
  32. 10
  33. pick a question to solve
  34. 54
  35. train the model
  36. 20
  37. correct bad labels
  38. 1
  39. 60
  40. recheck every label

Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students