← 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 181 · 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.📦 Arjun collected 150 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
  2. 2.⚖️ Two fruit sorter models were tested on the same 50 fruit photos. Model A got 45 right and Model B got 34 right. How many percentage points more accurate is Model A?
  3. 3.📦 Tara collected 50 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  4. 4.🧪 Why must you test a model on examples it has NOT seen? (a) to see if it learned (b) to make it faster (c) to save paper (d) to make it bigger
  5. 5.📦 Ananya collected 40 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  6. 6.📋 Planning an AI project: which comes first — pick a question to solve or fix it and test again? (a) pick a question to solve (b) fix it and test again
  7. 7.📦 Diya collected 110 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
  8. 8.📋 Planning an AI project: which comes first — improve data, retest or correct bad labels? (a) improve data, retest (b) correct bad labels
  9. 9.📋 Planning an AI project: which comes first — work out the accuracy or test on new photos? (a) work out the accuracy (b) test on new photos
  10. 10.📋 Planning an AI project: which comes first — work out the accuracy or improve data, retest? (a) work out the accuracy (b) improve data, retest
  11. 11.🎯 Tara’s handwriting reader is 60% accurate. If it is tested on 70 new handwritten letters, how many should it get right?
  12. 12.📦 Nisha collected 50 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  13. 13.🎯 Kabir’s fruit sorter is 60% accurate. If it is tested on 20 new fruit photos, how many should it get right?
  14. 14.📋 Planning an AI project: which comes first — gather many examples or train the model? (a) gather many examples (b) train the model
  15. 15.📋 Planning an AI project: which comes first — improve data, retest or set aside test photos? (a) improve data, retest (b) set aside test photos
  16. 16.📋 Planning an AI project: which comes first — split train and test or pick a question to solve? (a) split train and test (b) pick a question to solve
  17. 17.🎯 Aarav’s fruit sorter is 70% accurate. If it is tested on 90 new fruit photos, how many should it get right?
  18. 18.🎯 Vihaan’s spam spotter is 80% accurate. If it is tested on 60 new messages, how many should it get right?
  19. 19.📋 Planning an AI project: which comes first — recheck every label or test on new photos? (a) recheck every label (b) test on new photos
  20. 20.⚖️ Two handwriting reader models were tested on the same 25 handwritten letters. Model A got 24 right and Model B got 21 right. How many percentage points more accurate is Model A?
  21. 21.📋 Planning an AI project: which comes first — correct bad labels or calculate percent right? (a) correct bad labels (b) calculate percent right
  22. 22.📦 Vihaan collected 70 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  23. 23.🎯 Diya’s leaf identifier is 80% accurate. If it is tested on 20 new leaf photos, how many should it get right?
  24. 24.📋 Planning an AI project: which comes first — let it learn patterns or set aside test photos? (a) let it learn patterns (b) set aside test photos
  25. 25.❌ Aarav’s leaf identifier was tested on 39 new leaf photos and got 32 right. How many did it get wrong?
  26. 26.📋 Planning an AI project: which comes first — test on new photos or improve data, retest? (a) test on new photos (b) improve data, retest
  27. 27.🎯 Ishaan’s leaf identifier was tested on 25 new leaf photos and got 16 right. What is its accuracy in percent?
  28. 28.🎯 Meera’s spam spotter is 90% accurate. If it is tested on 10 new messages, how many should it get right?
  29. 29.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 25 right and Model B got 24 right. How many percentage points more accurate is Model A?
  30. 30.🧪 You can plan a simple AI project with… (a) only a big robot (b) nothing at all (c) paper and examples (d) a secret password
  31. 31.🎯 Tara’s leaf identifier was tested on 5 new leaf photos and got 5 right. What is its accuracy in percent?
  32. 32.📋 Planning an AI project: which comes first — label each example or improve data, retest? (a) label each example (b) improve data, retest
  33. 33.❌ Meera’s spam spotter was tested on 22 new messages and got 20 right. How many did it get wrong?
  34. 34.❌ Vihaan’s fruit sorter was tested on 21 new fruit photos and got 12 right. How many did it get wrong?
  35. 35.📋 Planning an AI project: which comes first — fix it and test again or pick a question to solve? (a) fix it and test again (b) pick a question to solve
  36. 36.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 24 right and Model B got 23 right. How many percentage points more accurate is Model A?
  37. 37.⚖️ Two spam spotter models were tested on the same 10 messages. Model A got 9 right and Model B got 6 right. How many percentage points more accurate is Model A?
  38. 38.🎯 Arjun’s leaf identifier was tested on 50 new leaf photos and got 49 right. What is its accuracy in percent?
  39. 39.📦 Ishaan collected 130 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  40. 40.📋 Planning an AI project: which comes first — collect fruit photos or set aside test photos? (a) collect fruit photos (b) set aside test photos

Answer key

  1. 120
  2. 22
  3. 40
  4. to see if it learned
  5. 32
  6. pick a question to solve
  7. 88
  8. correct bad labels
  9. test on new photos
  10. work out the accuracy
  11. 42
  12. 40
  13. 12
  14. gather many examples
  15. set aside test photos
  16. pick a question to solve
  17. 63
  18. 48
  19. recheck every label
  20. 12
  21. correct bad labels
  22. 56
  23. 16
  24. set aside test photos
  25. 7
  26. test on new photos
  27. 64
  28. 9
  29. 4
  30. paper and examples
  31. 100
  32. label each example
  33. 2
  34. 9
  35. pick a question to solve
  36. 4
  37. 30
  38. 98
  39. 104
  40. collect fruit photos

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