← 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 894 · 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.🎯 Aarav’s handwriting reader was tested on 10 new handwritten letters and got 6 right. What is its accuracy in percent?
  2. 2.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 39 right and Model B got 25 right. How many percentage points more accurate is Model A?
  3. 3.📋 Planning an AI project: which comes first — calculate percent right or fix it and test again? (a) calculate percent right (b) fix it and test again
  4. 4.🎯 Kabir’s leaf identifier was tested on 50 new leaf photos and got 39 right. What is its accuracy in percent?
  5. 5.🧪 You can plan a simple AI project with… (a) paper and examples (b) nothing at all (c) a secret password (d) only a big robot
  6. 6.🧪 What is accuracy? (a) total − correct (b) correct + total (c) total × 2 (d) correct ÷ total × 100
  7. 7.❌ Kabir’s recycling sorter was tested on 20 new waste photos and got 14 right. How many did it get wrong?
  8. 8.📋 Planning an AI project: which comes first — work out the accuracy or improve data, retest? (a) work out the accuracy (b) improve data, retest
  9. 9.📦 Vihaan collected 140 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
  10. 10.❌ Kabir’s leaf identifier was tested on 11 new leaf photos and got 10 right. How many did it get wrong?
  11. 11.🎯 Meera’s spam spotter is 80% accurate. If it is tested on 20 new messages, how many should it get right?
  12. 12.📋 Planning an AI project: which comes first — fix it and test again or work out the accuracy? (a) fix it and test again (b) work out the accuracy
  13. 13.📦 Meera collected 40 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  14. 14.🧪 Why must you test a model on examples it has NOT seen? (a) to save paper (b) to see if it learned (c) to make it faster (d) to make it bigger
  15. 15.📋 Planning an AI project: which comes first — improve data, retest or split train and test? (a) improve data, retest (b) split train and test
  16. 16.⚖️ Two spam spotter models were tested on the same 25 messages. Model A got 24 right and Model B got 22 right. How many percentage points more accurate is Model A?
  17. 17.⚖️ Two recycling sorter models were tested on the same 25 waste photos. Model A got 22 right and Model B got 19 right. How many percentage points more accurate is Model A?
  18. 18.📦 Diya collected 80 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  19. 19.❌ Ishaan’s recycling sorter was tested on 26 new waste photos and got 17 right. How many did it get wrong?
  20. 20.🎯 Vihaan’s bird-song app was tested on 50 new bird songs and got 26 right. What is its accuracy in percent?
  21. 21.📋 Planning an AI project: which comes first — collect fruit photos or recheck every label? (a) collect fruit photos (b) recheck every label
  22. 22.📋 Planning an AI project: which comes first — try unseen examples or train the model? (a) try unseen examples (b) train the model
  23. 23.📋 Planning an AI project: which comes first — improve data, retest or pick a question to solve? (a) improve data, retest (b) pick a question to solve
  24. 24.📋 Planning an AI project: which comes first — set aside test photos or pick a question to solve? (a) set aside test photos (b) pick a question to solve
  25. 25.❌ Aarav’s handwriting reader was tested on 31 new handwritten letters and got 22 right. How many did it get wrong?
  26. 26.📋 Planning an AI project: which comes first — improve data, retest or train the model? (a) improve data, retest (b) train the model
  27. 27.📦 Arjun collected 100 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  28. 28.📦 Vihaan collected 160 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  29. 29.❌ Nisha’s bird-song app was tested on 18 new bird songs and got 14 right. How many did it get wrong?
  30. 30.📦 Tara collected 190 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
  31. 31.📦 Ananya collected 50 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  32. 32.⚖️ Two bird-song app models were tested on the same 10 bird songs. Model A got 7 right and Model B got 5 right. How many percentage points more accurate is Model A?
  33. 33.🎯 Tara’s fruit sorter was tested on 4 new fruit photos and got 3 right. What is its accuracy in percent?
  34. 34.📋 Planning an AI project: which comes first — calculate percent right or let it learn patterns? (a) calculate percent right (b) let it learn patterns
  35. 35.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a louder speaker (b) fewer examples (c) more labelled examples (d) a new colour screen
  36. 36.⚖️ Two handwriting reader models were tested on the same 10 handwritten letters. Model A got 9 right and Model B got 6 right. How many percentage points more accurate is Model A?
  37. 37.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 23 right and Model B got 20 right. How many percentage points more accurate is Model A?
  38. 38.📋 Planning an AI project: which comes first — tag each photo by type or correct bad labels? (a) tag each photo by type (b) correct bad labels
  39. 39.🎯 Meera’s leaf identifier is 80% accurate. If it is tested on 50 new leaf photos, how many should it get right?
  40. 40.📦 Aarav collected 140 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?

Answer key

  1. 60
  2. 28
  3. calculate percent right
  4. 78
  5. paper and examples
  6. correct ÷ total × 100
  7. 6
  8. work out the accuracy
  9. 112
  10. 1
  11. 16
  12. work out the accuracy
  13. 32
  14. to see if it learned
  15. split train and test
  16. 8
  17. 12
  18. 64
  19. 9
  20. 52
  21. collect fruit photos
  22. train the model
  23. pick a question to solve
  24. pick a question to solve
  25. 9
  26. train the model
  27. 80
  28. 128
  29. 4
  30. 152
  31. 40
  32. 20
  33. 75
  34. let it learn patterns
  35. more labelled examples
  36. 30
  37. 12
  38. tag each photo by type
  39. 40
  40. 112

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